© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2003
    Prev
    Next
    INDEX
    Explanations

    the

    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
     frumos
    -0.47
    ียง
    -0.47
     quotidien
    -0.46
     banged
    -0.45
    initComponents
    -0.44
    yip
    -0.44
    indicato
    -0.43
     CGPoint
    -0.43
    温馨
    -0.43
     Puoi
    -0.43
    POSITIVE LOGITS
    OGND
    0.73
     مشين
    0.72
     وتسجيلات
    0.71
    MigrationBuilder
    0.71
     ویکی‌پدیا
    0.68
    帖最后由
    0.68
    AddTagHelper
    0.65
    NameInMap
    0.63
    SharedDtor
    0.63
    __*/
    0.60
    Activations Density 0.005%

    No Known Activations