Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74306
    Prev
    Next
    INDEX
    Explanations

    William

    np_max-act-logits · 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
    icznego
    -0.59
     Hoc
    -0.55
    وانید
    -0.51
    usehen
    -0.50
    spunkt
    -0.50
    iczny
    -0.48
    DJANGO
    -0.46
    Hoc
    -0.46
     whistles
    -0.45
    ssohn
    -0.45
    POSITIVE LOGITS
     שוליים
    0.69
     ModelExpression
    0.68
     صوتيه
    0.63
    enumi
    0.62
    makeConstraints
    0.56
    تفصیلات
    0.55
    DIPSETTING
    0.53
    setViewportView
    0.52
    expandindo
    0.52
     createSprite
    0.52
    Activations Density 0.160%

    No Known Activations