© 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. 44015
    Prev
    Next
    INDEX
    Explanations

    citations, technical writing

    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
     vectorielles
    -0.70
     extérieures
    -0.70
     métallique
    -0.66
     noires
    -0.65
     réfrig
    -0.65
     financières
    -0.65
     privados
    -0.65
     disparu
    -0.63
     vectorielle
    -0.61
     fermée
    -0.60
    POSITIVE LOGITS
     Gol
    0.63
     ?>">
    0.60
    rend
    0.57
    地说道
    0.56
    PrototypeOf
    0.56
    ?>">
    0.56
     control
    0.55
     Petro
    0.55
    esModule
    0.55
     Ruth
    0.55
    Activations Density 0.000%

    No Known Activations