© 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. 1-CLT-HP
    7. 434
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    ury
    -0.47
    uszka
    -0.47
    BuildContext
    -0.44
    muebles
    -0.40
     createState
    -0.39
     puol
    -0.38
     dře
    -0.38
    leville
    -0.37
    ագրություններ
    -0.37
    तु
    -0.37
    POSITIVE LOGITS
    reportWebVitals
    0.70
    queryInterface
    0.70
    awtextra
    0.65
     pituitary
    0.64
    Portail
    0.64
    ituitary
    0.63
    InvalidProtocol
    0.63
    othelioma
    0.61
     biopsies
    0.61
    الدراسه
    0.60
    Activations Density 0.061%

    No Known Activations