© 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. 5-CLT-HP
    7. 96190
    Prev
    Next
    INDEX
    Explanations

    mapping

    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
    MessageOf
    -0.79
    PerformLayout
    -0.70
    contentLoaded
    -0.69
    ValueStyle
    -0.68
    Дереккөздер
    -0.66
     Clans
    -0.60
    Lähteet
    -0.59
     للاسماء
    -0.57
     Савезне
    -0.57
    
    -0.57
    POSITIVE LOGITS
     new
    0.57
     ranges
    0.52
     another
    0.52
     some
    0.52
     numbers
    0.51
    tså
    0.51
     itself
    0.51
     nouve
    0.49
     rois
    0.48
     all
    0.48
    Activations Density 0.013%

    No Known Activations