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. 14166
    Prev
    Next
    INDEX
    Explanations

    words related to permissions, legal rights, and formal requests

    oai_token-act-pair · gemini-2.0-flash

    privilege

    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
    )])
    -0.50
    )\}
    -0.49
    nda
    -0.47
    ้น
    -0.45
     []).
    -0.45
    な
    -0.45
    cio
    -0.45
     isso
    -0.45
    olu
    -0.44
    amel
    -0.42
    POSITIVE LOGITS
     تانيه
    1.01
    الإنجليزية
    0.92
    expandindo
    0.86
    __":
    
    0.78
     AssemblyCulture
    0.75
    Kanpo
    0.75
    CodeDom
    0.73
     autorytatywna
    0.71
     الحره
    0.71
     estekak
    0.71
    Activations Density 15.857%

    No Known Activations