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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5465
    Prev
    Next
    INDEX
    Explanations

    that

    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
    Is
    -0.48
    Let
    -0.47
    的是
    -0.44
    lö
    -0.42
    let
    -0.41
    待
    -0.41
    form
    -0.40
    Ist
    -0.40
    oen
    -0.39
    回目の
    -0.39
    POSITIVE LOGITS
    出版年
    0.95
     ویکی‌پدیای
    0.79
     I
    0.71
    MENAFN
    0.71
    }\]
    0.69
     viendra
    0.69
    WriteTagHelper
    0.68
    astéroïdes
    0.67
     Мексичка
    0.66
    rrggbb
    0.66
    Activations Density 0.003%

    No Known Activations