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. 6021
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government and political parties and leadership roles

    oai_token-act-pair · gemini-2.0-flash

    words related to formal or official titles

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

    Secretaries/directors

    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
    AnchorStyles
    -0.69
    RenderAtEndOf
    -0.65
    ⓧ
    -0.64
    存于互联网档案馆
    -0.64
    spesies
    -0.59
    verständlich
    -0.58
    وفاته
    -0.57
    GraphicsUnit
    -0.57
    pona
    -0.57
    ///</
    -0.56
    POSITIVE LOGITS
     of
    0.83
    ungsbedingungen
    0.58
     hå
    0.48
     encabez
    0.47
     harapan
    0.46
     ejer
    0.45
    ย์
    0.45
     impegn
    0.44
     của
    0.44
     cuar
    0.44
    Activations Density 7.715%

    No Known Activations