© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2435
    Prev
    Next
    INDEX
    Explanations

    dropping

    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
     برانيه
    -0.79
    rrggbb
    -0.77
    出版年
    -0.67
     itſelf
    -0.64
    GHIJKLM
    -0.63
     pleaſure
    -0.58
    AndEndTag
    -0.56
    migrationBuilder
    -0.56
     للاسماء
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
     protoimpl
    0.55
    
    0.53
     Irrelevant
    0.52
     ivelany
    0.50
    COUVER
    0.49
     חיצוניים
    0.48
     almost
    0.46
     IDisposable
    0.45
    EXACT
    0.44
    相当
    0.43
    Activations Density 0.015%

    No Known Activations