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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38744
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.14
     reaſon
    -1.07
     houſe
    -1.03
     ſmall
    -1.02
     myſelf
    -1.02
     Monfieur
    -1.02
     poffe
    -1.02
     ſever
    -1.01
     ſtand
    -1.00
    RectangleBorder
    -1.00
    POSITIVE LOGITS
    ,
    0.79
     and
    0.71
     (
    0.71
     for
    0.69
     from
    0.69
    .
    0.68
     to
    0.67
    al
    0.67
    na
    0.66
     in
    0.65
    Activations Density 0.083%

    No Known Activations