© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1945
    Prev
    Next
    INDEX
    Explanations

    yna

    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
    
    -0.74
     cref
    -0.67
     AssemblyCulture
    -0.63
     initComponents
    -0.60
     coar
    -0.56
    )++;
    -0.55
    
    -0.55
     Barr
    -0.54
    WindowConstants
    -0.54
    enumii
    -0.54
    POSITIVE LOGITS
    psis
    0.65
     ویکی‌پدیا
    0.60
    pton
    0.59
    psin
    0.56
    pto
    0.54
    الحياه
    0.53
    psia
    0.51
    pses
    0.49
     financières
    0.46
    ptes
    0.45
    Activations Density 0.005%

    No Known Activations