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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16270
    Prev
    Next
    INDEX
    Explanations

    references to the fast food chain McDonalds and mentions of "drive throughs".

    oai_token-act-pair · gemini-2.0-flash

    fast food franchises

    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
    yntaxException
    -0.61
    aarrggbb
    -0.57
     يتيمه
    -0.50
    verwijspagina
    -0.49
    Epis
    -0.46
     pity
    -0.45
    hara
    -0.45
     furia
    -0.45
    vages
    -0.44
    itron
    -0.44
    POSITIVE LOGITS
     fast
    0.89
    Fast
    0.85
    fast
    0.85
     Fast
    0.84
     franchise
    0.76
    Franchise
    0.75
     Normdatei
    0.74
     FAST
    0.73
    FAST
    0.69
     Franchise
    0.67
    Activations Density 0.842%

    No Known Activations