© 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. 44140
    Prev
    Next
    INDEX
    Explanations

    Madhya

    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
    orm
    -0.81
     Oval
    -0.79
    ract
    -0.70
    AccessorTable
    -0.51
    īt
    -0.50
    uggle
    -0.50
     برانيه
    -0.50
    üyada
    -0.50
    tams
    -0.49
    sigkeit
    -0.49
    POSITIVE LOGITS
    HtmlAttribute
    0.87
    tvguidetime
    0.70
     arşivlendi
    0.64
     שוליים
    0.63
    
    0.62
    ריאה
    0.60
    Hochspringen
    0.59
     MainAxisSize
    0.59
     snippetHide
    0.57
    ніципа
    0.57
    Activations Density 0.170%

    No Known Activations