© 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

    method names, built-ins, keywords (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
    uples
    -0.15
    own
    -0.15
    ket
    -0.14
    up
    -0.14
    gth
    -0.12
    ul
    -0.09
    et
    -0.08
    kets
    -0.07
    ke
    -0.07
    ck
    -0.07
    Positive Logits
    si
    0.05
     ]↵
    0.03
     }↵
    0.03
     },↵
    0.03
    se
    0.03
    random
    0.02
     random
    0.02
    oin
    0.01
    temp
    0.01
    _values
    0.01
    Activations Density 98.166%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    swap assignment with brackets

    python-code · gemini-2.5-flash-lite

    list index operations or assignments (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
    (N
    -0.04
    _height
    -0.03
    09
    -0.03
    _distance
    -0.03
    _w
    -0.03
     dp
    -0.03
     route
    -0.02
    _pro
    -0.02
    ns
    -0.01
     w
    -0.01
    Positive Logits
    div
    0.06
    ld
    0.05
    _name
    0.05
    ood
    0.04
    _j
    0.04
    ad
    0.04
    add
    0.04
    _i
    0.04
    q
    0.04
    _string
    0.04
    Activations Density 99.999%

    No Known Activations