© 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. 44004
    Prev
    Next
    INDEX
    Explanations

    do

    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
     a
    -0.67
     an
    -0.59
     do
    -0.58
     doing
    -0.57
     did
    -0.52
     up
    -0.50
    RegistryLite
    -0.50
    done
    -0.49
    doing
    -0.49
     due
    -0.48
    POSITIVE LOGITS
    ergies
    0.90
     you
    0.85
     ainfi
    0.75
     作者
    0.71
     otomatig
    0.70
    liothèque
    0.70
    WebVitals
    0.69
     vôtre
    0.68
     autorité
    0.67
    indest
    0.66
    Activations Density 0.143%

    No Known Activations