© 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. 4-CLT-HP
    7. 4568
    Prev
    Next
    INDEX
    Explanations

    Programming questions

    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
    还会
    -0.39
     updated
    -0.39
     interviewed
    -0.38
    還會
    -0.36
    updating
    -0.36
     updating
    -0.35
     ruling
    -0.35
     upgraded
    -0.35
     shares
    -0.34
     hosted
    -0.34
    POSITIVE LOGITS
    MigrationBuilder
    0.85
     صوتيه
    0.83
    SourceChecksum
    0.80
    Grab
    0.79
     Simply
    0.79
    __':
    0.79
     '\\;'
    0.78
    Simply
    0.76
     للاسماء
    0.74
     First
    0.73
    Activations Density 0.007%

    No Known Activations