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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16331
    Prev
    Next
    INDEX
    Explanations

    words associated with analytical research in various domains

    oai_token-act-pair · gemini-2.0-flash

    research/analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    RectangleBorder
    -0.78
     الحره
    -0.75
    AsUp
    -0.70
     للمعارف
    -0.66
    antaine
    -0.62
    SBATCH
    -0.60
    InputBorder
    -0.60
     itſelf
    -0.59
     DriverManager
    -0.59
     تضيفلها
    -0.58
    POSITIVE LOGITS
    SourceChecksum
    0.54
     cser
    0.49
    agram
    0.49
    formazioni
    0.48
     immédi
    0.48
     independent
    0.48
    <eos>
    0.48
    GENERATED
    0.47
    امية
    0.47
     voeren
    0.47
    Activations Density 4.665%

    No Known Activations