© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15498
    Prev
    Next
    INDEX
    Explanations

    references to structured data formats and coding code snippets

    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
    izers
    -1.44
    isers
    -1.22
    iser
    -1.08
    httphttps
    -0.85
    ISER
    -0.82
    IsContent
    -0.80
     ujednoznacz
    -0.78
    tanleria
    -0.77
    IsMutable
    -0.77
    脚注の使い方
    -0.76
    POSITIVE LOGITS
    Pey
    1.16
    Topic
    0.98
     Peyton
    0.71
    Topics
    0.61
    izer
    0.55
    <0xDC>
    0.53
    mphs
    0.49
    زی
    0.47
    sies
    0.46
     inflamed
    0.45
    Activations Density 0.007%

    No Known Activations