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. 97911
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
     work
    -1.56
     have
    -0.96
     trabajo
    -0.94
    work
    -0.93
     Work
    -0.92
     trabalho
    -0.91
     lavoro
    -0.91
     travail
    -0.90
    Work
    -0.90
     WORK
    -0.82
    POSITIVE LOGITS
    
    0.56
    options
    0.55
     Waray
    0.55
    transQ
    0.53
    JspWriter
    0.52
    pertino
    0.51
    Vedi
    0.50
     Савезне
    0.50
    hyrchwyd
    0.50
     against
    0.50
    Activations Density 1.071%

    No Known Activations