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. 1559
    Prev
    Next
    INDEX
    Explanations

    financial jargon, especially related to companies and markets

    oai_token-act-pair · gemini-2.0-flash

    Business/Financial news

    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
    TargetException
    -0.75
    MLLoader
    -0.69
    XmlAccessorType
    -0.68
    XMLSchema
    -0.61
     Référence
    -0.59
    SEE
    -0.57
    \{\\
    -0.57
     PopupWindow
    -0.57
     Baillargeon
    -0.56
     top
    -0.55
    POSITIVE LOGITS
    enumii
    0.72
    ForValue
    0.52
    ValueStyle
    0.52
    annica
    0.52
     AssemblyCulture
    0.51
     चुनें
    0.49
     aanbod
    0.47
    PerPage
    0.47
    +#+#
    0.47
    ⓘ
    0.46
    Activations Density 5.838%

    No Known Activations