© 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. 94526
    Prev
    Next
    INDEX
    Explanations

    go

    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
    ↵↵
    -0.63
    ↵
    -0.59
     
    -0.54
    the
    -0.49
     (
    -0.48
    '
    -0.44
    出版年
    -0.40
     -
    -0.37
     N
    -0.37
     lead
    -0.37
    POSITIVE LOGITS
     HasFactory
    1.01
     feroit
    0.88
    NUMX
    0.81
     resourceCulture
    0.78
     Anſ
    0.78
     Reſ
    0.77
    StoreMessageInfo
    0.77
     Theſe
    0.76
    帖最后由
    0.75
    RegressionTest
    0.75
    Activations Density 0.313%

    No Known Activations