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. 2122
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and publication citations

    oai_token-act-pair · gemini-2.0-flash

    respectively

    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
     referenties
    -0.71
     poffe
    -0.69
    IndentedString
    -0.68
    脚注の使い方
    -0.63
     purpoſe
    -0.62
     Jefus
    -0.61
     RSSSF
    -0.61
     fhort
    -0.61
     respectively
    -0.60
     NDEBUG
    -0.60
    POSITIVE LOGITS
    bilità
    0.46
    YSTEM
    0.46
    cyn
    0.43
    ومت
    0.42
     منظ
    0.42
     getSystem
    0.42
    SetItem
    0.41
     Drapeau
    0.41
     régi
    0.41
    alam
    0.41
    Activations Density 1.282%

    No Known Activations