© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45281
    Prev
    Next
    INDEX
    Explanations

    of

    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
     AssemblyCulture
    -0.77
    IsContent
    -0.63
     Gea
    -0.62
    /*
    -0.60
     فريبيس
    -0.56
     GeoNames
    -0.55
    UrlResolution
    -0.55
    المناصب
    -0.54
    انيف
    -0.54
     Baillargeon
    -0.54
    POSITIVE LOGITS
    CELLANEOUS
    0.57
    ChildScrollView
    0.52
    ждународ
    0.51
    Ход
    0.51
    عاية
    0.50
    RSpec
    0.49
    tablissements
    0.49
     تانيه
    0.49
    Население
    0.49
    </tfoot>
    0.48
    Activations Density 0.206%

    No Known Activations