© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38783
    Prev
    Next
    INDEX
    Explanations

    attempt

    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
    MemoryWarning
    -0.81
    ReusableCell
    -0.81
    AsUp
    -0.78
    IBarButtonItem
    -0.76
     cherchés
    -0.71
     ویکی‌پدی
    -0.71
     Roskov
    -0.71
    enumii
    -0.68
    kloped
    -0.68
     tartalomajánló
    -0.68
    POSITIVE LOGITS
     to
    1.01
    <bos>
    0.81
     taking
    0.61
     re
    0.58
     placing
    0.57
     a
    0.56
     giving
    0.56
     getting
    0.55
     suggesting
    0.54
     offering
    0.53
    Activations Density 0.097%

    No Known Activations