© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74727
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act-logits · 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
     previously
    -0.86
     prior
    -0.77
     had
    -0.73
     previous
    -0.71
     initially
    -0.71
     earlier
    -0.69
     auparavant
    -0.69
    previous
    -0.66
     Had
    -0.66
    previously
    -0.65
    POSITIVE LOGITS
    WebVitals
    0.68
    rrggbb
    0.63
     itſelf
    0.57
    weetened
    0.55
     الرياضيه
    0.54
    loài
    0.54
    %</
    0.54
    RTEX
    0.53
     pleaſure
    0.52
    舺
    0.52
    Activations Density 0.001%

    No Known Activations