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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14152
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medicine and the body

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    <bos>
    -0.80
    AddTagHelper
    -0.47
    ValueStyle
    -0.45
    autoconfigure
    -0.43
     propOrder
    -0.43
    makeText
    -0.41
    liwości
    -0.40
    prefixer
    -0.40
    MessageState
    -0.40
    المشاركات
    -0.40
    POSITIVE LOGITS
    DoubleQuotes
    0.76
    )++;
    0.68
     fufficient
    0.68
    ]--;
    0.68
    ędziesz
    0.65
    ouge
    0.63
     ddelweddau
    0.63
    ologic
    0.63
    gares
    0.61
     cop
    0.61
    Activations Density 14.670%

    No Known Activations