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. 1-CLT-HP
    4. 102
    Prev
    Next
    INDEX
    Explanations

    writing and literature

    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
     writing
    -0.63
     write
    -0.57
    Write
    -0.55
     readers
    -0.54
     scrivere
    -0.54
     writer
    -0.53
     menulis
    -0.52
    write
    -0.52
     author
    -0.50
     escre
    -0.50
    POSITIVE LOGITS
    :]:
    0.85
     "..\..\..\
    0.77
    __":
    
    0.71
     kasarigan
    0.69
    __":
    0.68
    PerformLayout
    0.68
     通販
    0.66
    Portály
    0.66
     吋
    0.64
     noqa
    0.63
    Activations Density 0.025%

    No Known Activations