© 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. 43817
    Prev
    Next
    INDEX
    Explanations

    novice

    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
    <![
    -0.70
    исленность
    -0.69
    økt
    -0.68
    ImageContext
    -0.67
    PerformLayout
    -0.65
     '\\;'
    -0.65
    KURZBESCHREIBUNG
    -0.65
    PRNewswire
    -0.65
     MainAxisSize
    -0.64
    ngdoc
    -0.63
    POSITIVE LOGITS
    ations
    0.71
    son
    0.67
    ars
    0.62
    ins
    0.59
    mi
    0.58
    ation
    0.56
    bal
    0.54
    rat
    0.54
    so
    0.53
    ari
    0.53
    Activations Density 0.128%

    No Known Activations