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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16233
    Prev
    Next
    INDEX
    Explanations

    job

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

    words and phrases related to employment and events which affect it

    oai_token-act-pair · gemini-2.0-flash

    job

    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
    FormTagHelper
    -0.65
     laboral
    -0.62
     الاطلاع
    -0.61
     employment
    -0.59
     occupations
    -0.58
     gospod
    -0.55
    Profession
    -0.54
     mattino
    -0.53
     workplaces
    -0.53
     économie
    -0.52
    POSITIVE LOGITS
    \{\\
    0.63
    awtextra
    0.63
     nahilalakip
    0.62
    IntoConstraints
    0.59
    قایناق‌لار
    0.53
    verwijspagina
    0.50
    //</
    0.48
     Po
    0.48
     '&
    0.47
    ниципа
    0.47
    Activations Density 4.547%

    No Known Activations