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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14014
    Prev
    Next
    INDEX
    Explanations

    the prefix "sil", and in some instances the words Black Silhouette and Hildergard

    oai_token-act-pair · 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
     CreateTagHelper
    -0.57
    rovnik
    -0.56
    TagMode
    -0.51
     getopt
    -0.50
    Personendaten
    -0.49
     disambiguazione
    -0.49
    Unmarshaller
    -0.49
    featureID
    -0.48
    ExecuteReader
    -0.48
     désolés
    -0.48
    POSITIVE LOGITS
     costado
    0.52
    ówno
    0.52
    出版年
    0.52
     الدولى
    0.52
    
    0.50
    🏾
    0.49
     NKC
    0.49
    ListOf
    0.49
     벡터
    0.48
     ejercicio
    0.48
    Activations Density 0.446%

    No Known Activations