Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16273
    Prev
    Next
    INDEX
    Explanations

    sentences describing awards

    oai_token-act-pair · gemini-2.0-flash

    awarding

    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
    poto
    -0.48
    省市镇
    -0.48
     réalisation
    -0.48
     هيا
    -0.48
     فريبيس
    -0.48
    ніципалі
    -0.47
    ernalia
    -0.46
    առ
    -0.46
    CompleteListener
    -0.45
     بيها
    -0.44
    POSITIVE LOGITS
     handed
    1.12
     handing
    1.09
     handout
    1.06
     awarded
    1.01
     awarding
    1.00
     handouts
    0.94
     distribution
    0.91
     Awarded
    0.90
     distribute
    0.90
     distributing
    0.89
    Activations Density 1.375%

    No Known Activations