© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    Br

    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
    发表于
    -0.58
     most
    -0.54
    matchCondition
    -0.47
     lead
    -0.47
    poel
    -0.47
    glide
    -0.47
     Compostela
    -0.45
     illegal
    -0.44
     Biôgrafia
    -0.43
     resistance
    -0.42
    POSITIVE LOGITS
    OGND
    0.82
    uxxxx
    0.78
    createServer
    0.63
    tvguidetime
    0.60
    URLException
    0.57
    bkz
    0.57
    InjectAttribute
    0.57
     كومونز
    0.56
    <?
    0.54
    Quiénes
    0.54
    Activations Density 0.003%

    No Known Activations