© 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. 39949
    Prev
    Next
    INDEX
    Explanations

    Black

    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
     Black
    -2.25
     black
    -2.13
    Black
    -2.06
     BLACK
    -1.84
    black
    -1.83
    BLACK
    -1.71
    黑
    -1.45
     schwarzen
    -1.36
    的黑
    -1.32
     schwarze
    -1.28
    POSITIVE LOGITS
    smith
    0.90
    windowFixed
    0.90
    s
    0.85
    sheets
    0.84
     <<<<<<<<<<<<<<
    0.83
    ened
    0.81
    swell
    0.78
    ENED
    0.77
    ness
    0.76
    MigrationBuilder
    0.75
    Activations Density 0.064%

    No Known Activations