© 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. 986
    Prev
    Next
    INDEX
    Explanations

    diet

    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
     diet
    -1.24
     mass
    -1.05
     Diet
    -0.94
    ga
    -0.92
     dia
    -0.87
    diet
    -0.84
    Diet
    -0.79
    dia
    -0.77
     dieting
    -0.73
     Dia
    -0.68
    POSITIVE LOGITS
    TintMode
    0.73
    mybatisplus
    0.68
     estimés
    0.66
     Nacionales
    0.63
     comigo
    0.63
    Tikang
    0.62
     pleaſure
    0.60
     ModelExpression
    0.59
     ویکی‌پدیای
    0.59
     himſelf
    0.57
    Activations Density 0.164%

    No Known Activations