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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11066
    Prev
    Next
    INDEX
    Explanations

    locations and family history, especially related to graveyards

    oai_token-act-pair · gemini-2.0-flash

    terms related to documentation or references

    np_token-act-pair-logits · gpt-4o-mini

    programming references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     pesa
    -0.54
    RegressionTest
    -0.52
     çat
    -0.49
     DESCRIPT
    -0.49
    tagHelperRunner
    -0.48
     vuonna
    -0.48
     bombar
    -0.48
    TypedDataSet
    -0.48
     totem
    -0.48
     äta
    -0.48
    POSITIVE LOGITS
    Kaynakça
    0.66
     InputDecoration
    0.56
    Referanser
    0.53
    ANTLR
    0.50
    mockito
    0.49
    indro
    0.49
    alyptus
    0.49
     nakalista
    0.48
     useState
    0.48
    webElement
    0.48
    Activations Density 0.326%

    No Known Activations