© 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. 91131
    Prev
    Next
    INDEX
    Explanations

    Android code

    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
     noastre
    -0.54
     ře
    -0.54
    Diweddarwch
    -0.53
     المعيارى
    -0.53
    NCS
    -0.52
     سكانية
    -0.51
    <?>>
    -0.51
     comerciais
    -0.50
    benar
    -0.50
     Ruskin
    -0.50
    POSITIVE LOGITS
     transférez
    0.68
     للاسماء
    0.62
     HomeScreen
    0.57
     CanadaChoose
    0.56
    SharedDtor
    0.56
    出版年
    0.53
    principalColumn
    0.53
    Biographie
    0.51
    FXMLLoader
    0.51
    ++)
    0.50
    Activations Density 0.727%

    No Known Activations