© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    open with arguments

    python-code · gemini-2.5-flash-lite

    for loop iteration variable (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ied
    -0.05
    zero
    -0.05
    cond
    -0.05
    ded
    -0.05
     remaining
    -0.05
    ange
    -0.04
     last
    -0.04
    ted
    -0.04
    valid
    -0.03
    orted
    -0.03
    Positive Logits
    En
    0.02
    ]),
    0.02
     connections
    0.02
    xp
    0.01
    rc
    0.01
    ine
    0.01
     ob
    0.01
    ])
    0.01
    act
    0.01
    ])↵
    0.01
    Activations Density 99.725%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    'lo' followed by comma

    python-code · gemini-2.5-flash-lite

    len() function call (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    alculate
    -0.02
    enerate
    -0.02
     calculate
    -0.02
     find
    -0.02
     generate
    -0.01
     create
    -0.01
     Calculate
    -0.01
    ulate
    -0.01
     Find
    -0.01
     dfs
    -0.01
    Positive Logits
    oard
    0.02
    aze
    0.02
    blem
    0.02
    grid
    0.02
    _grid
    0.02
     grid
    0.02
     graph
    0.02
    udoku
    0.02
     maze
    0.02
    .grid
    0.02
    Activations Density 44.889%

    No Known Activations