© 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. 20-CLT-HP
    7. 78172
    Prev
    Next
    INDEX
    Explanations

    contained

    np_max-act-logits · 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
     vectorielles
    -0.65
     définiti
    -0.64
     capacités
    -0.56
     supérieures
    -0.56
     églises
    -0.53
     loisirs
    -0.52
     stratégies
    -0.52
     particulières
    -0.52
     récents
    -0.51
     renseignements
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.94
     is
    0.83
     amounts
    0.81
     recalls
    0.74
     архивлан
    0.73
    Portail
    0.73
     bids
    0.69
     leads
    0.69
     calls
    0.68
     fixes
    0.68
    Activations Density 0.004%

    No Known Activations