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. 0-RES-MATRYOSHKA-DC
    4. 14552
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving derivatives, derivatives, or calculus notation

    oai_token-act-pair · gpt-4.1-nano
    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
    ^(@)
    -2.72
     itſelf
    -2.58
     Efq
    -2.45
     myſelf
    -2.42
     Мексичка
    -2.41
    NUMX
    -2.41
     $_"
    -2.34
     Forumite
    -2.27
    ſelves
    -2.23
     ―――――
    -2.20
    POSITIVE LOGITS
    .
    1.90
    ↵↵
    1.73
    ↵
    1.70
    -
    1.69
    <eos>
    1.63
    (
    1.63
    /
    1.55
    ,
    1.54
     (
    1.45
    :
    1.44
    Activations Density 0.047%

    No Known Activations