Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74329
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     DBNull
    -0.65
    #+#
    -0.64
    __*/
    -0.63
     estimés
    -0.58
    WebElementEntity
    -0.56
    endregion
    -0.55
    AutoresizingMask
    -0.54
    GEBURTSDATUM
    -0.54
    TypedDataSet
    -0.53
     dieux
    -0.53
    POSITIVE LOGITS
     переписи
    0.55
     Protective
    0.49
     ziren
    0.48
     aids
    0.48
     chi̍t
    0.47
    ikä
    0.47
     saites
    0.45
    itinéraire
    0.45
     Eul
    0.44
    furl
    0.44
    Activations Density 0.001%

    No Known Activations