© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 41061
    Prev
    Next
    INDEX
    Explanations

    estimated

    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
     وتسجيلات
    -0.93
    />";
    -0.91
     للاسماء
    -0.78
     Majefty
    -0.73
    ".
    
    -0.73
    قایناقلار
    -0.73
     Réponses
    -0.72
     bezeichneter
    -0.72
    "];
    
    -0.71
    }$​
    -0.69
    POSITIVE LOGITS
     of
    0.69
    <bos>
    0.57
     Of
    0.50
     rentrer
    0.49
    G
    0.46
    ↵↵
    0.45
     saites
    0.44
    L
    0.44
     parco
    0.43
    Of
    0.43
    Activations Density 0.031%

    No Known Activations