© 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. 91133
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     attentes
    -0.69
     prochaines
    -0.69
     précédentes
    -0.66
     blessés
    -0.62
     escuchadas
    -0.61
     vœux
    -0.61
     bénévoles
    -0.60
     récents
    -0.59
     mères
    -0.59
     supérieures
    -0.59
    POSITIVE LOGITS
     चीज़ों
    0.53
    mybatisplus
    0.49
     decks
    0.47
     processes
    0.46
     frites
    0.46
     courses
    0.46
    <bos>
    0.45
    peu
    0.45
    khar
    0.45
     Aene
    0.45
    Activations Density 0.007%

    No Known Activations