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. 14131
    Prev
    Next
    INDEX
    Explanations

    mentions of medical imaging techniques

    oai_token-act-pair · gemini-2.0-flash

    medical imaging

    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
     X
    -1.36
    X
    -1.23
     x
    -1.16
    x
    -0.96
    X
    -0.94
    setX
    -0.78
    getX
    -0.77
     getX
    -0.77
    XX
    -0.72
    x
    -0.71
    POSITIVE LOGITS
    TextBoxColumn
    0.64
    पया
    0.64
    Personensuche
    0.63
    帖最后由
    0.62
     ISNI
    0.58
     ContentValues
    0.58
    AccessorTable
    0.57
    ByVersion
    0.56
    élica
    0.56
    qvarna
    0.56
    Activations Density 2.209%

    No Known Activations