© 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. 39882
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
     infrequently
    -1.19
     themſelves
    -1.13
     pleaſure
    -1.09
     freely
    -1.09
     himſelf
    -1.08
     Jefus
    -1.08
     consistently
    -1.04
     Majefty
    -1.02
     regularly
    -1.02
     safely
    -1.02
    POSITIVE LOGITS
     called
    0.43
    bankan
    0.43
    équ
    0.42
     sold
    0.42
     ve
    0.41
     naar
    0.41
     held
    0.40
     put
    0.40
    openSession
    0.40
     sent
    0.39
    Activations Density 0.102%

    No Known Activations