© 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. 15986
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     étoient
    -0.73
     hadapan
    -0.65
     avoient
    -0.62
     venons
    -0.62
     énergé
    -0.61
     fermés
    -0.61
    warnai
    -0.60
     ferons
    -0.60
     fréqu
    -0.59
     découver
    -0.58
    POSITIVE LOGITS
     crocodiles
    0.66
     crocodile
    0.57
     feathers
    0.57
     felling
    0.57
     crows
    0.57
     leopard
    0.57
     gator
    0.56
     lances
    0.56
     alligator
    0.56
     skis
    0.56
    Activations Density 0.001%

    No Known Activations