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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40802
    Prev
    Next
    INDEX
    Explanations

    growth and/or reduction

    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
     يتيمه
    -0.90
    aarrggbb
    -0.82
     '\\;'
    -0.74
     equinox
    -0.73
     تضيفلها
    -0.72
     pinulongan
    -0.71
    bewerken
    -0.69
    醐
    -0.69
     SIMBAD
    -0.68
     itſelf
    -0.68
    POSITIVE LOGITS
    JdbcTemplate
    0.45
     if
    0.45
    ServletException
    0.44
     brand
    0.44
    Примечания
    0.44
     or
    0.43
    ها
    0.39
    parseLong
    0.38
     in
    0.38
    EqualsAnd
    0.38
    Activations Density 0.025%

    No Known Activations