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. 2132
    Prev
    Next
    INDEX
    Explanations

    place names, especially street names and business names, alongside associated terms like "report."

    oai_token-act-pair · gemini-2.0-flash

    South East Asia travel/food reviews

    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
    WithIOException
    -0.48
    AutoresizingMask
    -0.45
     marks
    -0.44
    Marks
    -0.44
     Marks
    -0.44
    JpaRepository
    -0.43
     MARKS
    -0.42
    OrBuilder
    -0.42
     voyez
    -0.42
    craper
    -0.42
    POSITIVE LOGITS
    Datuak
    0.60
     Réponses
    0.59
     Merton
    0.59
     beginnetje
    0.57
     autorytatywna
    0.53
    argout
    0.53
    edizione
    0.52
    SqlClient
    0.51
    enment
    0.51
    tesy
    0.51
    Activations Density 0.543%

    No Known Activations