© 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. 44046
    Prev
    Next
    INDEX
    Explanations

    Vladimir

    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
    Negative Logits
     ankles
    -0.69
    IBOutlet
    -0.57
    nosa
    -0.54
    ANDUM
    -0.50
     unregulated
    -0.50
    ods
    -0.49
     coron
    -0.48
     fle
    -0.48
    DED
    -0.48
    으로
    -0.48
    POSITIVE LOGITS
    abestanden
    0.63
    expandindo
    0.63
    ViewFeatures
    0.56
    jfree
    0.53
     виправивши
    0.53
    cipar
    0.52
    -------------</
    0.52
    IGraphics
    0.52
    orsese
    0.51
     صوتيه
    0.50
    Activations Density 0.031%

    No Known Activations