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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14136
    Prev
    Next
    INDEX
    Explanations

    different topics and words, including medical conditions, elections and programming terms

    oai_token-act-pair · gemini-2.0-flash

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     XNUMX
    -0.84
    WebElementEntity
    -0.81
    دانشنامهٔ
    -0.77
    abetes
    -0.72
    GEBURTS
    -0.71
    stdc
    -0.68
    brainly
    -0.67
     XCTest
    -0.66
     snippetHide
    -0.64
    beiros
    -0.64
    POSITIVE LOGITS
    <bos>
    0.94
     igång
    0.62
     digitais
    0.62
     laikā
    0.55
     positifs
    0.53
     supérieurs
    0.53
    áda
    0.53
     générations
    0.53
     anaknya
    0.52
     próprias
    0.51
    Activations Density 4.159%

    No Known Activations