Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2330
    Prev
    Next
    INDEX
    Explanations

    personal finance or real estate terms, especially in the context of offering advice or services.

    oai_token-act-pair · gemini-2.0-flash

    Finding a service/professional

    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
    itative
    -0.47
    uders
    -0.44
     dre
    -0.43
     def
    -0.41
    ITUTION
    -0.41
     Tan
    -0.41
     ویکی‌آمباردا
    -0.40
    ört
    -0.40
    ément
    -0.40
    othelial
    -0.40
    POSITIVE LOGITS
     <>",
    0.82
    InjectAttribute
    0.73
     AssemblyCompany
    0.71
     betweenstory
    0.69
     defaultstate
    0.69
    Vidite
    0.68
    DockStyle
    0.66
    EndGlobalSection
    0.65
     Exacts
    0.64
    oa̍t
    0.63
    Activations Density 9.549%

    No Known Activations