© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    h.head attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access or `import` statement

    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
    ighbour
    -0.26
     with
    -0.22
    27
    -0.21
     elif
    -0.21
    26
    -0.19
    300
    -0.18
    _with
    -0.18
    .remove
    -0.17
    Ħ
    -0.15
    param
    -0.15
    POSITIVE LOGITS
    cess
    0.11
     mo
    0.10
    du
    0.09
     [(
    0.07
    ackage
    0.07
    _distance
    0.07
    ath
    0.06
    ari
    0.06
     ne
    0.05
    95
    0.05
    Activations Density 99.990%

    No Known Activations