© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43441
    Prev
    Next
    INDEX
    Explanations

    code/technical snippets

    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
    mya
    -2.94
    m
    -0.78
     ویکی‌پدیا
    -0.71
    h
    -0.69
    y
    -0.65
    c
    -0.64
    k
    -0.63
    AntiForgeryToken
    -0.60
     ReactDOM
    -0.60
    e
    -0.56
    POSITIVE LOGITS
    PointerException
    0.65
     suprême
    0.58
    arcoma
    0.57
     Murdock
    0.55
    AnchorTagHelper
    0.53
     "));
    0.52
    uley
    0.52
    giers
    0.52
    "]));
    0.52
    agrad
    0.51
    Activations Density 0.221%

    No Known Activations