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. 0-CLT-HP
    4. 91550
    Prev
    Next
    INDEX
    Explanations

    wolf

    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
    ina
    -0.83
    INA
    -0.66
    wolf
    -0.59
    shadow
    -0.56
    Rüyada
    -0.56
    olina
    -0.55
    faßt
    -0.54
    出版年
    -0.53
     Shadow
    -0.52
    GARET
    -0.52
    POSITIVE LOGITS
    ed
    0.68
    GOTREF
    0.65
    +:+
    0.64
     gddr
    0.58
    RectangleBorder
    0.57
    \{\\
    0.55
    ized
    0.55
    ayant
    0.55
     sement
    0.54
     Commande
    0.54
    Activations Density 0.382%

    No Known Activations