© 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. 0-CLT-HP
    7. 95299
    Prev
    Next
    INDEX
    Explanations

    works

    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
    Works
    -1.09
    works
    -0.99
    WORKS
    -0.92
    PostExecute
    -0.63
     CURIAM
    -0.62
    RectangleBorder
    -0.61
    createConnection
    -0.61
    存于互联网档案馆
    -0.60
    usermodel
    -0.60
     Houſe
    -0.60
    POSITIVE LOGITS
     betweenstory
    0.61
    ngOn
    0.57
    wapV
    0.52
     ویکی‌پدیای
    0.50
     CreateTagHelper
    0.49
    ponses
    0.48
    UrlResolution
    0.48
     In
    0.47
    adillas
    0.47
    chiato
    0.46
    Activations Density 0.974%

    No Known Activations