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. 1-CLT-HP
    4. 45078
    Prev
    Next
    INDEX
    Explanations

    selle

    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
    QM
    -0.55
    mire
    -0.54
    ρεύ
    -0.52
    ieri
    -0.51
    modus
    -0.50
    
    -0.48
    dotenv
    -0.48
    mett
    -0.46
    otide
    -0.46
    onus
    -0.46
    POSITIVE LOGITS
    SharedCtor
    0.63
    StoryboardSegue
    0.57
     ſever
    0.56
     iſt
    0.55
     للمعارف
    0.55
     itſelf
    0.54
     breakfasts
    0.54
    InstanceState
    0.54
    __);
    0.53
    rsiniz
    0.52
    Activations Density 0.024%

    No Known Activations