© 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

    math module functions

    python-code · gemini-2.5-flash-lite

    .sqrt() or ._* (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
    rom
    -0.06
    ize
    -0.06
    udent
    -0.06
    ilities
    -0.06
    param
    -0.05
    iz
    -0.05
    args
    -0.05
    osition
    -0.05
    ized
    -0.05
    ork
    -0.04
    Positive Logits
    lat
    0.05
    inal
    0.05
     population
    0.04
    print
    0.04
    dividual
    0.04
    endoftext
    0.04
    rite
    0.04
    opulation
    0.04
    _population
    0.04
                   
    0.04
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
    .
    -0.06
    _
    -0.05
    (
    -0.04
    \
    -0.03
    <extra_output_id:2047>
    -0.03
    [
    -0.02
    ().
    -0.02
     {↵
    -0.02
    da
    -0.02
    .strip
    -0.02
    Positive Logits
    split
    0.11
    cond
    0.11
    lit
    0.10
    strip
    0.09
     representing
    0.07
    irst
    0.07
    alse
    0.06
     that
    0.05
     given
    0.05
     >=
    0.05
    Activations Density 4.787%

    No Known Activations