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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4334
    Prev
    Next
    INDEX
    Explanations

    copyright and github links

    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
    initComponents
    -0.56
     "..\..\..\
    -0.53
    ecake
    -0.52
    parsedMessage
    -0.51
     uruguay
    -0.50
     Wund
    -0.50
    pology
    -0.49
    >//
    -0.49
    出版年
    -0.49
    moiselle
    -0.49
    POSITIVE LOGITS
    saraba
    0.54
    UserScript
    0.53
    PMailer
    0.53
     AssemblyCompany
    0.49
     Vote
    0.49
    Rhestr
    0.49
     wrote
    0.49
    SourceChecksum
    0.47
     ویکی‌پدیای
    0.47
    原标题
    0.47
    Activations Density 0.070%

    No Known Activations