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-CLT-HP
    4. 74005
    Prev
    Next
    INDEX
    Explanations

    Medical terminology

    np_max-act-logits · 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
     Monfieur
    -0.58
    ſelf
    -0.57
     Shakspeare
    -0.55
    WriteTagHelper
    -0.55
     esqu
    -0.54
     fences
    -0.54
    Geplaatst
    -0.54
     yonder
    -0.54
     habari
    -0.53
     >=",
    -0.53
    POSITIVE LOGITS
    osis
    0.50
    derma
    0.46
    참고
    0.45
    AndEndTag
    0.44
    PropertyGroup
    0.43
    {#
    0.43
    SQLiteDatabase
    0.42
    otic
    0.42
    columna
    0.42
    orro
    0.42
    Activations Density 0.004%

    No Known Activations