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. 11118
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with a variety of unrelated opinions and views.

    oai_token-act-pair · gemini-2.0-flash

    the phrase "teacher" and related expressions

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

    Kinds of people

    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
    UnusedPrivate
    -0.69
     estekak
    -0.68
     GenerationType
    -0.62
    thâu
    -0.62
    脚注の使い方
    -0.61
     referrerpolicy
    -0.59
     resourceCulture
    -0.59
    ราะ
    -0.59
     Catawiki
    -0.57
     snippetHide
    -0.57
    POSITIVE LOGITS
     par
    0.71
     through
    0.52
     by
    0.52
     BY
    0.50
    par
    0.50
    Par
    0.49
     Par
    0.49
     in
    0.48
     Through
    0.47
     try
    0.45
    Activations Density 2.750%

    No Known Activations