Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39151
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Parab
    -0.68
     étoit
    -0.66
     føl
    -0.64
     vidare
    -0.64
    utives
    -0.64
    cknow
    -0.63
    autoconfigure
    -0.62
     समीक्षक
    -0.61
    
    -0.61
    ebenarnya
    -0.60
    POSITIVE LOGITS
    er
    0.60
    able
    0.59
    a
    0.56
    ment
    0.55
    ability
    0.54
    th
    0.51
    tow
    0.51
    de
    0.50
    o
    0.50
    in
    0.49
    Activations Density 0.207%

    No Known Activations