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. 8-RES-MATRYOSHKA-DC
    4. 31215
    Prev
    Next
    INDEX
    Explanations

    the phrase "I have" followed by a word

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     оригіналу
    -0.59
    httphttps
    -0.57
     riuscito
    -0.57
    يميديا
    -0.56
     riusc
    -0.54
    Примітки
    -0.53
     hinaus
    -0.53
    кисло
    -0.50
    ğın
    -0.50
     tắc
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.77
    :✨
    0.66
     <>",
    0.66
     newBuilder
    0.65
    InjectAttribute
    0.63
    LikeLike
    0.62
    *</
    0.61
     <<<<<<<<<<<<<<
    0.60
    WebElementEntity
    0.60
     autorytatywna
    0.60
    Activations Density 0.032%

    No Known Activations