© 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. 4-CLT-HP
    7. 3516
    Prev
    Next
    INDEX
    Explanations

    by

    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
    DockStyle
    -0.83
     disambiguazione
    -0.69
    AsUp
    -0.63
     ujednoznacz
    -0.63
    ThroughAttribute
    -0.60
    homonymie
    -0.59
    ########.
    -0.59
    点此举报
    -0.59
     lenker
    -0.57
     <>",
    -0.57
    POSITIVE LOGITS
     Efq
    0.60
     sogni
    0.59
     firſt
    0.57
     esportivo
    0.57
     uſed
    0.56
     preſent
    0.56
     ſame
    0.56
     greateſt
    0.55
     cauſe
    0.54
     Grosvenor
    0.54
    Activations Density 0.003%

    No Known Activations