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. 5994
    Prev
    Next
    INDEX
    Explanations

    sentences with several conjunctions, especially "and" and "or", suggesting lists

    oai_token-act-pair · gemini-2.0-flash

    common verbs and commands

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

    and

    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
     and
    -0.73
    Viited
    -0.54
     or
    -0.53
    and
    -0.52
    not
    -0.51
    oo
    -0.46
     And
    -0.45
     diyor
    -0.45
     
    -0.44
    Not
    -0.43
    POSITIVE LOGITS
    Geplaatst
    0.81
     remember
    0.77
    FormTagHelper
    0.76
    RenderAtEndOf
    0.75
     uſe
    0.73
     grab
    0.72
     send
    0.70
    uxxxx
    0.70
     get
    0.70
    encodeWith
    0.70
    Activations Density 1.834%

    No Known Activations