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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5910
    Prev
    Next
    INDEX
    Explanations

    instances of the word "deal" and its various forms.

    oai_token-act-pair · gemini-2.0-flash

    terms indicating resolution or resolution processes

    np_token-act-pair-logits · gpt-4o-mini

    deal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    phs
    -0.51
    WRAP
    -0.49
     aguda
    -0.48
    misión
    -0.47
    icals
    -0.46
    richtungen
    -0.46
     dég
    -0.46
     amely
    -0.45
     engraçadas
    -0.45
     liev
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.71
    IndentedString
    0.67
    HasColumnType
    0.67
     فريبيس
    0.67
    FormTagHelper
    0.66
     AssemblyProduct
    0.61
    Бахар
    0.61
     المعيارى
    0.60
    Autoritní
    0.58
    География
    0.57
    Activations Density 1.918%

    No Known Activations