© 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. 1-CLT-HP
    7. 15858
    Prev
    Next
    INDEX
    Explanations

    in

    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
    go
    -0.54
    z
    -0.53
    ness
    -0.51
    ous
    -0.47
    za
    -0.47
    ing
    -0.47
    tait
    -0.46
    ting
    -0.46
    ging
    -0.45
    gear
    -0.44
    POSITIVE LOGITS
    mybatisplus
    0.81
    IUrlHelper
    0.79
    ADELPHIA
    0.77
     ExecuteAsync
    0.77
    帖最后由
    0.73
    setVerticalGroup
    0.73
     @"/
    0.72
    WebVitals
    0.71
     surla
    0.71
     ModelExpression
    0.70
    Activations Density 0.031%

    No Known Activations