© 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. 4-CLT-HP
    7. 2193
    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
     <<
    -0.87
    <<
    -0.79
    <<"
    -0.67
    +#+
    -0.62
    ,«
    -0.59
     мәкал
    -0.56
     ‹
    -0.55
     <<<
    -0.53
    出版年
    -0.53
    <<<<
    -0.52
    POSITIVE LOGITS
    Chham
    0.58
     poster
    0.56
     Вікіпе
    0.56
     hObject
    0.55
    ATIVA
    0.55
     root
    0.54
     Gué
    0.54
    舎
    0.53
    ableView
    0.53
    تفصیلات
    0.53
    Activations Density 0.018%

    No Known Activations