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. 6023
    Prev
    Next
    INDEX
    Explanations

    legal and business language, especially surrounding patents and claims

    oai_token-act-pair · gemini-2.0-flash

    words related to combinations or arrangements

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

    Legal texts

    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
     épaules
    -0.81
     lèvres
    -0.73
     enfans
    -0.72
     genoux
    -0.72
     marquées
    -0.72
     célèbres
    -0.70
     vägen
    -0.70
     barnen
    -0.70
     dieux
    -0.69
     connus
    -0.69
    POSITIVE LOGITS
     arrangement
    0.84
     background
    0.79
     mixture
    0.79
    })*/
    0.77
    #+#
    0.77
     solution
    0.77
     division
    0.76
    ")){
    
    0.75
     combination
    0.74
     information
    0.74
    Activations Density 12.549%

    No Known Activations