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. 4-CLT-HP
    4. 3748
    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
     ModelExpression
    -0.62
     nakalista
    -0.59
    ,
    -0.57
    .");
    
    -0.56
    )";
    
    -0.55
     ویکی‌آمباردا
    -0.55
    )';
    -0.55
    enumi
    -0.54
    >";
    
    -0.54
     */
    
    
    -0.54
    POSITIVE LOGITS
     acrylique
    0.51
    MLLoader
    0.50
     tiens
    0.47
     Primarily
    0.47
     Soon
    0.47
     Mostly
    0.46
    UMNS
    0.46
     Sometime
    0.46
     Mainly
    0.45
     Posteriormente
    0.45
    Activations Density 0.002%

    No Known Activations