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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1603
    Prev
    Next
    INDEX
    Explanations

    words related to an eye surgery procedure

    oai_token-act-pair · gemini-2.0-flash

    Eyes/Ophthalmology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     AssemblyTitle
    -0.60
    NameInMap
    -0.50
    resave
    -0.48
    sprzed
    -0.48
     TimeUnit
    -0.47
    umumkan
    -0.47
     Lordships
    -0.46
    atguigu
    -0.46
    pi
    -0.46
    yntaxException
    -0.45
    POSITIVE LOGITS
    adaptiveStyles
    0.70
    httphttps
    0.65
     Allociné
    0.58
    chter
    0.56
     تضيفلها
    0.54
    CRI
    0.50
    clerview
    0.50
    szön
    0.49
     ProtoMessage
    0.48
    KommentareTeilen
    0.48
    Activations Density 7.778%

    No Known Activations