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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14135
    Prev
    Next
    INDEX
    Explanations

    the possessive pronouns "their," "your," and "own," sometimes in combination, and sometimes with words associated with "liberal".

    oai_token-act-pair · gemini-2.0-flash

    Taking action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    发表于
    -0.67
    IConfiguration
    -0.57
    ématiques
    -0.54
    kuuta
    -0.53
    autés
    -0.51
    Notae
    -0.50
    Access
    -0.50
    手中的
    -0.48
    endregion
    -0.47
    WithIdentifier
    -0.47
    POSITIVE LOGITS
    eleste
    0.69
     lubric
    0.54
     zirc
    0.54
     Hinge
    0.54
    netbeans
    0.54
     Estuary
    0.52
     unclean
    0.52
    TestTools
    0.51
     الحره
    0.51
    >*/
    0.51
    Activations Density 0.888%

    No Known Activations