Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14009
    Prev
    Next
    INDEX
    Explanations

    the number 8 followed by other digits

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.87
     متعلقه
    -0.83
    LLocation
    -0.71
    oneofs
    -0.68
    Datuak
    -0.66
     consultato
    -0.66
    ttino
    -0.65
    ArrowToggle
    -0.64
    httphttps
    -0.64
     للمعارف
    -0.61
    POSITIVE LOGITS
    ικ
    0.52
    יות
    0.52
     grunn
    0.52
     Nauk
    0.52
    escal
    0.51
    erequisites
    0.51
    zeln
    0.51
     żyw
    0.50
    Nonnull
    0.50
    bzero
    0.49
    Activations Density 0.231%

    No Known Activations