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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 372
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     "
    -1.48
     “
    -1.40
     the
    -0.99
     a
    -0.99
     (
    -0.96
     
    -0.94
     in
    -0.91
     for
    -0.91
     his
    -0.90
     so
    -0.90
    POSITIVE LOGITS
    تقاوى
    1.34
    )");
    
    1.23
    >");
    
    1.18
    ...");
    
    1.16
    '},
    
    1.16
    "},
    
    1.16
    )";
    
    1.13
    >';
    
    1.13
     Мексичка
    1.12
    "]);
    
    1.09
    Activations Density 0.529%

    No Known Activations