© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15266
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
    ViewImports
    -0.60
     quæ
    -0.59
     vœux
    -0.57
     sèche
    -0.56
    awtextra
    -0.56
    umentación
    -0.55
    therape
    -0.54
     gereja
    -0.54
     endblock
    -0.53
     liitty
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.51
    InvalidProtocol
    0.51
    prüche
    0.49
    providedIn
    0.48
    δες
    0.47
     Jord
    0.47
     ""],
    0.46
    rugada
    0.44
    '])
    0.43
     مشين
    0.42
    Activations Density 0.005%

    No Known Activations