© 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. 5-CLT-HP
    7. 95251
    Prev
    Next
    INDEX
    Explanations

    us/let's

    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
     NDEBUG
    -0.59
    KEYCODE
    -0.57
    WebVitals
    -0.53
     Aram
    -0.52
     незавершена
    -0.52
     Theſe
    -0.51
    hésite
    -0.50
     faulting
    -0.49
     étrang
    -0.49
     ſche
    -0.49
    POSITIVE LOGITS
     consider
    0.60
     examine
    0.58
     now
    0.57
     begin
    0.56
     look
    0.54
     suppose
    0.54
    ammans
    0.52
     først
    0.52
     investigate
    0.52
     introduce
    0.52
    Activations Density 0.009%

    No Known Activations