© 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. 39994
    Prev
    Next
    INDEX
    Explanations

    Code/document formatting

    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
    ¦
    -1.09
     ¦
    -0.90
    ly
    -0.49
      
    -0.49
     (
    -0.47
     
    -0.46
    -
    -0.45
    phosa
    -0.45
     Reverso
    -0.45
     culture
    -0.44
    POSITIVE LOGITS
    ]]=
    0.78
    EDEFAULT
    0.77
     '\\;'
    0.77
    }\]
    0.76
    ).__
    0.75
    titleMargin
    0.73
     تانيه
    0.72
    DockStyle
    0.70
    msgTypes
    0.69
    Tembelea
    0.69
    Activations Density 0.468%

    No Known Activations