© 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. 94862
    Prev
    Next
    INDEX
    Explanations

    by

    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
     Schaefer
    -0.57
     Select
    -0.54
     choose
    -0.51
    raught
    -0.50
     select
    -0.49
     Choose
    -0.48
     buying
    -0.47
    特急
    -0.47
     tell
    -0.47
    ίδ
    -0.46
    POSITIVE LOGITS
     Administrativna
    0.71
    出版年
    0.63
     ویکی‌پدیا
    0.63
    +#+
    0.60
    ViewImports
    0.59
     AspNetCore
    0.57
    DockStyle
    0.57
    ReusableCell
    0.56
    devamını
    0.56
     disambiguazione
    0.56
    Activations Density 0.002%

    No Known Activations