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. 12637
    Prev
    Next
    INDEX
    Explanations

    southwest

    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
    ThroughAttribute
    -0.59
    gman
    -0.54
    ToScroll
    -0.52
    Southwest
    -0.51
    delwed
    -0.51
     Southwest
    -0.51
    stdc
    -0.50
    DoubleQuotes
    -0.49
    rosh
    -0.49
     виправивши
    -0.49
    POSITIVE LOGITS
     архивлан
    0.55
    )».
    0.55
    一体
    0.53
    )»
    0.52
    queous
    0.50
     snippetHide
    0.50
     BaseActivity
    0.49
    >";
    
    0.49
    Istorija
    0.48
     जहां
    0.48
    Activations Density 0.237%

    No Known Activations