© 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. 13164
    Prev
    Next
    INDEX
    Explanations

    Code and copyright notices

    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
    itism
    -1.66
    ########.
    -0.49
    ophilia
    -0.43
    tez
    -0.41
     ویکی‌پدیا
    -0.41
     além
    -0.39
    esModule
    -0.39
    ęp
    -0.39
     primo
    -0.39
    CPtr
    -0.39
    POSITIVE LOGITS
    出版年
    0.75
     nakalista
    0.72
     للمعارف
    0.70
     CreateTagHelper
    0.65
    enumii
    0.64
     EconPapers
    0.63
     ExecuteAsync
    0.60
     sown
    0.60
    somewhere
    0.58
    Personensuche
    0.58
    Activations Density 0.052%

    No Known Activations