© 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. 1-CLT-HP
    7. 45603
    Prev
    Next
    INDEX
    Explanations

    art

    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
     to
    -0.83
     in
    -0.75
     and
    -0.62
     or
    -0.60
     (
    -0.58
     by
    -0.56
     as
    -0.56
    ,
    -0.56
     on
    -0.55
    cshtml
    -0.54
    POSITIVE LOGITS
     Reſ
    0.90
     greateſt
    0.88
     pleaſure
    0.88
     ſmall
    0.85
     Monfieur
    0.85
     uſe
    0.82
     ſeveral
    0.81
     reaſon
    0.81
     Theſe
    0.81
     myſelf
    0.79
    Activations Density 0.610%

    No Known Activations