© 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. 91162
    Prev
    Next
    INDEX
    Explanations

    in

    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
     princípio
    -0.68
     siguran
    -0.68
     obfer
    -0.65
     creș
    -0.63
     jöv
    -0.63
     kasarigan
    -0.62
     lampada
    -0.62
     mitään
    -0.62
     aikaa
    -0.62
     huom
    -0.62
    POSITIVE LOGITS
     يتيمه
    0.66
     المعيارى
    0.61
     that
    0.57
     serving
    0.57
     تضيفلها
    0.56
     the
    0.56
     using
    0.56
    iastes
    0.54
     causing
    0.54
     most
    0.53
    Activations Density 0.115%

    No Known Activations