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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45595
    Prev
    Next
    INDEX
    Explanations

    palladium

    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
    estacks
    -0.74
    structors
    -0.68
    cotch
    -0.61
    digans
    -0.60
    olingo
    -0.60
    évaluateur
    -0.57
    ographers
    -0.57
    foundland
    -0.57
     anten
    -0.56
    RTRS
    -0.56
    POSITIVE LOGITS
    TypedDataSet
    0.54
    Przypisy
    0.46
     oprot
    0.45
    XmlAccessorType
    0.44
    ритори
    0.43
    ्त
    0.42
    opensource
    0.40
    dostęp
    0.40
    yu
    0.40
    es
    0.40
    Activations Density 0.175%

    No Known Activations