© 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. 15440
    Prev
    Next
    INDEX
    Explanations

    references to specific structural gaps or spaces in materials or processes

    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
    
    -0.74
    TProtocol
    -0.61
     EconPapers
    -0.60
     муніципалі
    -0.59
     FormsModule
    -0.58
    expandindo
    -0.56
    shadowOpacity
    -0.56
     ReactDOM
    -0.56
    HostException
    -0.56
     cherchés
    -0.55
    POSITIVE LOGITS
     gaps
    2.00
     Gaps
    1.68
    gaps
    1.62
     spaces
    0.61
     vid
    0.56
    mybatisplus
    0.55
     AspNetCore
    0.51
     cát
    0.51
     ddelweddau
    0.50
    例文帳に追加
    0.50
    Activations Density 0.001%

    No Known Activations