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. 31237
    Prev
    Next
    INDEX
    Explanations

    capitalized words, especially names, or words that could be parts of names

    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
     Mal
    -0.64
    enskap
    -0.64
    gin
    -0.62
     nắm
    -0.62
     InputDecoration
    -0.61
    prech
    -0.60
     FIC
    -0.60
     Ring
    -0.58
    urtstag
    -0.58
     Cunningham
    -0.58
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
     BIBSYS
    0.86
    Hozzáférés
    0.85
     SAE
    0.85
     Jefus
    0.84
     juſ
    0.83
     Erich
    0.82
     vulgaires
    0.82
    <!--[
    0.82
     Klon
    0.82
    Activations Density 0.415%

    No Known Activations