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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95888
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Administrativna
    -0.55
    談社
    -0.52
     дописавши
    -0.52
    CppMethod
    -0.50
    tanleria
    -0.49
    はじめに
    -0.47
     ModelExpression
    -0.46
    databinding
    -0.46
    herin
    -0.45
     Familiar
    -0.44
    POSITIVE LOGITS
    antMatchers
    0.65
    migrationBuilder
    0.63
    apimachinery
    0.60
     vPvB
    0.59
    ToAction
    0.59
     BorderRadius
    0.58
     trovar
    0.56
    ThroughAttribute
    0.54
     giocare
    0.53
    sbereich
    0.53
    Activations Density 0.003%

    No Known Activations