© 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. 1-CLT-HP
    7. 8893
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     prêtres
    -0.64
     dieux
    -0.63
     brancas
    -0.59
     lèvres
    -0.57
     tiroirs
    -0.56
     vœux
    -0.54
     pères
    -0.54
     bénévoles
    -0.54
     sogni
    -0.54
     chrétiens
    -0.53
    POSITIVE LOGITS
    optarg
    0.61
    íti
    0.60
     Shetland
    0.57
     GenerationType
    0.57
     benefited
    0.57
     numbers
    0.56
     casting
    0.56
     Dacia
    0.55
     orientations
    0.55
     orientation
    0.55
    Activations Density 0.042%

    No Known Activations