© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    knowledge

    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
     fais
    -0.48
     navigu
    -0.47
     Catawiki
    -0.47
    cobra
    -0.46
    WireFormat
    -0.46
    iprot
    -0.46
    enfone
    -0.42
    TableHead
    -0.42
     فريبيس
    -0.42
    parametrize
    -0.41
    POSITIVE LOGITS
    Personensuche
    0.66
     gap
    0.63
    θα
    0.60
     shared
    0.60
    gap
    0.59
     gaps
    0.59
     nugget
    0.59
    zone
    0.58
     internetowa
    0.57
    CloseOperation
    0.57
    Activations Density 0.001%

    No Known Activations