© 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
    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
    ].
    -0.05
    s
    -0.05
    ↵        ↵
    -0.04
     break
    -0.04
     order
    -0.04
     as
    -0.03
            ↵
    -0.03
    ns
    -0.03
    section
    -0.03
    ure
    -0.02
    Positive Logits
    o
    0.13
    own
    0.12
     o
    0.12
    oc
    0.11
    od
    0.10
    ok
    0.10
    ore
    0.09
    ow
    0.07
    ho
    0.07
    over
    0.07
    Activations Density 7.467%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    logical operator `and` in conditions

    python-code · gemini-2.5-flash-lite

    variable assignment or attribute access (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
     instruction
    -0.06
     instructions
    -0.05
    struction
    -0.04
    age
    -0.04
    structions
    -0.04
    mory
    -0.03
    class
    -0.03
    [start
    -0.03
    gist
    -0.03
    (start
    -0.03
    Positive Logits
    alse
    0.05
    loat
    0.05
    uples
    0.04
    own
    0.04
    up
    0.04
    inal
    0.04
    qrt
    0.04
    ery
    0.04
    č
    0.03
    rite
    0.03
    Activations Density 100.000%

    No Known Activations