© 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. 1-CLT-HP
    7. 12144
    Prev
    Next
    INDEX
    Explanations

    spec

    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
     spec
    -0.90
     specifications
    -0.87
     Specification
    -0.84
     specification
    -0.83
     Specifications
    -0.78
    Specification
    -0.77
     specs
    -0.77
     Spec
    -0.73
    Specifications
    -0.70
     SPECIFICATION
    -0.68
    POSITIVE LOGITS
    ########.
    0.69
     '\\;'
    0.68
     Roskov
    0.64
    TemporalType
    0.63
     الدولى
    0.61
    fromCharCode
    0.60
    MigrationBuilder
    0.59
    foria
    0.57
     ContentValues
    0.57
    出版年
    0.57
    Activations Density 0.018%

    No Known Activations