© 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. 1-CLT-HP
    7. 15920
    Prev
    Next
    INDEX
    Explanations

    rare

    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
     StringVar
    -0.63
     Réponses
    -0.56
     raiſ
    -0.50
     quæ
    -0.48
     deſt
    -0.48
     Daß
    -0.47
    styleable
    -0.47
     fevere
    -0.47
    ฏ
    -0.46
    новништво
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.65
     numberOfRows
    0.55
    седа
    0.55
    PreferredItem
    0.49
     disponibilités
    0.48
     in
    0.48
    UserScript
    0.48
    ChildScrollView
    0.47
    __':
    0.47
    SPONSORED
    0.46
    Activations Density 0.018%

    No Known Activations