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. 14129
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and texts

    oai_token-act-pair · gemini-2.0-flash

    Religious texts and authors

    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
     Propriété
    -0.57
    ophosph
    -0.56
    XmlAccessType
    -0.52
    OGND
    -0.52
    fjspx
    -0.50
    xFFFFFF
    -0.50
     Livraison
    -0.50
    addCriterion
    -0.49
    xffffff
    -0.49
     Clair
    -0.49
    POSITIVE LOGITS
    DoubleQuotes
    0.57
    (")");
    0.55
    Javadoc
    0.53
    '>{
    0.50
    }*/
    0.49
    ()])
    0.48
     referrerpolicy
    0.48
    İstinadlar
    0.48
    Referencies
    0.48
    hoeddwyd
    0.47
    Activations Density 0.234%

    No Known Activations