© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1066
    Prev
    Next
    INDEX
    Explanations

    year assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment and comparison operators

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    distances
    -0.31
    jac
    -0.26
    _distances
    -0.25
    etween
    -0.24
    distan
    -0.23
     Calculate
    -0.23
     distances
    -0.22
    distance
    -0.20
     between
    -0.20
    erge
    -0.19
    POSITIVE LOGITS
     us
    0.14
    ip
    0.11
    [-
    0.08
     en
    0.08
     u
    0.07
     as
    0.06
    la
    0.06
    (m
    0.04
    q
    0.03
    '
    0.00
    Activations Density 100.000%

    No Known Activations