© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3479
    Prev
    Next
    INDEX
    Explanations

    6

    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
     referenties
    -0.67
     pleaſure
    -0.67
     مشين
    -0.66
     tolerated
    -0.62
     AssemblyCulture
    -0.62
     fevere
    -0.61
     ویکی‌پدی
    -0.60
     purpoſe
    -0.60
     nakalista
    -0.60
     سكانية
    -0.59
    POSITIVE LOGITS
    .
    0.54
     berjudul
    0.49
     célèbres
    0.45
     Cataloging
    0.44
     Rigidbody
    0.42
    enumi
    0.42
    AsyncResult
    0.41
     pessoais
    0.41
    WaitGroup
    0.41
     rêves
    0.40
    Activations Density 0.159%

    No Known Activations