© 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. 5-CLT-HP
    7. 6275
    Prev
    Next
    INDEX
    Explanations

    better/improved

    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
     préféré
    -0.59
     épar
    -0.59
     garanzia
    -0.59
     récents
    -0.58
     fallu
    -0.56
     mejoras
    -0.56
     séjours
    -0.56
     costado
    -0.56
     sœurs
    -0.55
     améliorer
    -0.55
    POSITIVE LOGITS
     ways
    0.73
    ways
    0.63
     treatment
    0.62
     management
    0.60
    voked
    0.58
    cokinetics
    0.56
     trained
    0.56
    cited
    0.54
    treated
    0.54
     methods
    0.53
    Activations Density 0.001%

    No Known Activations