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. 9-RES-MATRYOSHKA-DC
    4. 16490
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation.

    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
    ResponseWriter
    -0.50
    Résumé
    -0.49
    <?
    -0.48
    Portail
    -0.47
     sàng
    -0.45
    &=&\
    -0.45
    falfa
    -0.45
    errHandler
    -0.44
     الرياضيه
    -0.43
    ös
    -0.43
    POSITIVE LOGITS
     تانيه
    0.67
     мәкал
    0.66
    kuuta
    0.63
     članak
    0.60
    تقاوى
    0.58
    ControllerTest
    0.58
     Seeder
    0.58
    UIAlert
    0.56
    esterno
    0.54
     Dall
    0.53
    Activations Density 0.029%

    No Known Activations