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. 16336
    Prev
    Next
    INDEX
    Explanations

    instances of requesting and demanding something

    oai_token-act-pair · gemini-2.0-flash

    request

    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
    expandindo
    -0.75
    RegressionTest
    -0.75
    تقاوى
    -0.69
     OMITBAD
    -0.63
     defaultstate
    -0.63
     himo
    -0.63
    DeleteBehavior
    -0.60
    OGND
    -0.60
    modelBuilder
    -0.58
     Lightboxes
    -0.58
    POSITIVE LOGITS
     malu
    0.55
    AttributeSet
    0.54
     soigne
    0.52
    contributors
    0.50
     asylum
    0.50
     parole
    0.48
     valenci
    0.48
     a
    0.47
     Waterloo
    0.46
     reconn
    0.46
    Activations Density 3.059%

    No Known Activations