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. 16307
    Prev
    Next
    INDEX
    Explanations

    instances of obligation or requirement

    oai_token-act-pair · gemini-2.0-flash

    "to be", "must be"

    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
     BoxFit
    -0.66
     AssemblyCulture
    -0.65
    rungsseite
    -0.65
     StatelessWidget
    -0.63
    IconModule
    -0.63
     StatefulWidget
    -0.59
    ]--;
    -0.59
    fjspx
    -0.56
     Formosa
    -0.56
    setHas
    -0.56
    POSITIVE LOGITS
     Wicidata
    0.63
    eky
    0.52
    fromnode
    0.50
    venta
    0.50
    Coordenadas
    0.48
    vent
    0.47
    mtx
    0.46
     xuất
    0.46
    ably
    0.45
    vento
    0.45
    Activations Density 1.756%

    No Known Activations