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. 16760
    Prev
    Next
    INDEX
    Explanations

    math problems, focusing on quotients represented by the word "divided" and/or division symbols, and any potential remainders.

    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
     Signalez
    -0.69
    Xna
    -0.55
     provisoire
    -0.55
    httphttps
    -0.54
    Identyfik
    -0.52
    Bibliograf
    -0.51
    andExpect
    -0.50
    IUrlHelper
    -0.48
    WriteBarrier
    -0.47
     NSCoder
    -0.47
    POSITIVE LOGITS
    PMailer
    0.56
     FetchType
    0.56
    tagHelper
    0.55
    ouncil
    0.54
     tartalomajánló
    0.54
    Cuáles
    0.53
     yym
    0.53
    ("")]
    
    0.53
     '\\;'
    0.53
    calaure
    0.53
    Activations Density 0.014%

    No Known Activations