© 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. 0-CLT-HP
    7. 92170
    Prev
    Next
    INDEX
    Explanations

    usually

    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
     Usually
    -1.09
    Usually
    -1.09
    usually
    -1.04
     usually
    -1.00
     Majefty
    -0.97
     itſelf
    -0.96
     Jefus
    -0.95
     biasanya
    -0.92
     houſe
    -0.89
     myſelf
    -0.89
    POSITIVE LOGITS
     BoxDecoration
    0.69
     means
    0.49
     an
    0.47
     cherchés
    0.47
     has
    0.47
     the
    0.46
     فريبيس
    0.46
    setViewportView
    0.44
    TagHelper
    0.44
    ↵
    0.44
    Activations Density 1.585%

    No Known Activations