© 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. 20-CLT-HP
    7. 78023
    Prev
    Next
    INDEX
    Explanations

    code and calculations

    np_max-act-logits · 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
     until
    -2.52
    until
    -2.23
    Until
    -2.20
     Until
    -2.17
     UNTIL
    -1.97
     till
    -1.95
     hasta
    -1.81
     jusqu
    -1.80
     untill
    -1.73
    Till
    -1.66
    POSITIVE LOGITS
    noin
    0.48
    dders
    0.48
    cotch
    0.45
    anthin
    0.43
     Akbar
    0.42
     gesso
    0.42
    ctically
    0.41
    pper
    0.40
    tez
    0.40
    ppie
    0.40
    Activations Density 0.003%

    No Known Activations