© 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. 492
    Prev
    Next
    INDEX
    Explanations

    utian

    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
    تقاوى
    -0.79
     виправивши
    -0.77
    forName
    -0.65
    utian
    -0.65
    stein
    -0.63
    httphttps
    -0.59
     odkazy
    -0.59
    MediaStore
    -0.58
     braccia
    -0.56
     nargin
    -0.54
    POSITIVE LOGITS
    opcional
    0.54
    ainville
    0.52
    nachron
    0.50
     BeautifulSoup
    0.49
    luent
    0.48
    izarea
    0.47
    řeba
    0.47
     faudrait
    0.47
    entyfik
    0.46
    layui
    0.46
    Activations Density 0.006%

    No Known Activations