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. 39177
    Prev
    Next
    INDEX
    Explanations

    industries and materials

    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
     largely
    -0.46
     mostly
    -0.43
     mainly
    -0.42
     for
    -0.41
     absent
    -0.41
     fiducia
    -0.41
     primarily
    -0.40
    صدر
    -0.39
     bucal
    -0.39
     missing
    -0.39
    POSITIVE LOGITS
    ConstraintMaker
    1.10
     مرئيه
    0.87
     EconPapers
    0.86
     Houſe
    0.78
    ScopeManager
    0.76
     Reſ
    0.75
    esgue
    0.74
     Diſ
    0.71
    DockStyle
    0.71
    /***/
    0.71
    Activations Density 0.043%

    No Known Activations