© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95501
    Prev
    Next
    INDEX
    Explanations

    (

    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
    mend
    -2.05
    mended
    -1.04
    脚注の使い方
    -0.85
    Mend
    -0.70
    MigrationBuilder
    -0.68
    mende
    -0.66
    mendation
    -0.65
     doInBackground
    -0.63
    يكب
    -0.60
    WillAppear
    -0.57
    POSITIVE LOGITS
    a
    0.64
    s
    0.54
     Ceramby
    0.52
    en
    0.52
    i
    0.50
    um
    0.49
    IUrlHelper
    0.49
    [
    0.48
    ur
    0.48
    вей
    0.47
    Activations Density 0.035%

    No Known Activations