© 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

    comma in argument lists

    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
    /
    -0.12
     /
    -0.08
     //
    -0.07
    pected
    -0.06
    _total
    -0.05
    otal
    -0.05
    cep
    -0.05
     base
    -0.05
    total
    -0.05
     total
    -0.04
    Positive Logits
     W
    0.14
     Graph
    0.13
     E
    0.13
     F
    0.12
     If
    0.12
     V
    0.12
     St
    0.12
     Ex
    0.12
     R
    0.11
     T
    0.11
    Activations Density 79.809%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    lambda function definition

    python-code · gemini-2.5-flash-lite

    number or string literal (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
    Ã
    -0.03
    ')↵↵
    -0.02
    ))↵↵
    -0.02
     whi
    -0.02
    ])↵↵
    -0.02
    ")↵↵
    -0.02
    }")<|
    -0.02
    "↵↵
    -0.02
    }")↵↵
    -0.02
    )↵↵
    -0.02
    Positive Logits
    ake
    0.05
    isit
    0.05
    im
    0.05
    ast
    0.04
    ain
    0.04
    valu
    0.04
     nx
    0.04
    lace
    0.04
    chedule
    0.04
    out
    0.03
    Activations Density 100.000%

    No Known Activations