© 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. 1190
    Prev
    Next
    INDEX
    Explanations

    sticker

    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
    arshal
    -0.53
     Kontrol
    -0.51
    ştir
    -0.50
    WEBPACK
    -0.48
     standardized
    -0.47
     ferons
    -0.47
     Capsule
    -0.46
     tourné
    -0.46
    tilor
    -0.46
     standardised
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.71
     ་་
    0.67
     pleaſure
    0.67
    complexContent
    0.65
    SharedDtor
    0.65
     renewal
    0.61
    GTCX
    0.61
     uska
    0.61
     onlyOwner
    0.60
     Jefus
    0.60
    Activations Density 0.083%

    No Known Activations