© 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. 95705
    Prev
    Next
    INDEX
    Explanations

    places

    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
     Jersey
    -0.82
     norm
    -0.75
     jersey
    -0.74
    Jersey
    -0.67
     JERSEY
    -0.66
     Meksiku
    -0.65
     Winaray
    -0.65
    jersey
    -0.64
     HasFactory
    -0.63
     Norm
    -0.62
    POSITIVE LOGITS
    Xna
    0.68
    York
    0.63
     York
    0.57
    таратура
    0.52
    ↵↵
    0.50
     YORK
    0.50
    rungsseite
    0.49
    DrawerToggle
    0.45
    IntoConstraints
    0.45
    Portail
    0.45
    Activations Density 0.394%

    No Known Activations