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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16198
    Prev
    Next
    INDEX
    Explanations

    Gisaeng

    np_token-act-pair-logits · gemini-2.0-flash

    words related to dance and choreography and other performances

    oai_token-act-pair · gemini-2.0-flash

    dance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    ########.
    -0.88
     unknownFields
    -0.85
     AssemblyProduct
    -0.81
     Италијани
    -0.80
    afficheront
    -0.78
     AssemblyCulture
    -0.77
    الحياه
    -0.76
    mergeFrom
    -0.75
    berdayakan
    -0.73
    ChildScrollView
    -0.73
    POSITIVE LOGITS
    ito
    0.48
     term
    0.46
    løs
    0.44
    walde
    0.44
    Kit
    0.42
     wy
    0.41
    lop
    0.41
    cythe
    0.41
    шку
    0.41
     history
    0.40
    Activations Density 3.584%

    No Known Activations