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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 941
    Prev
    Next
    INDEX
    Explanations

    text sections that refer to scientific studies and citations

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.78
    ValueStyle
    -0.76
     cherchés
    -0.76
    новништво
    -0.75
    الإنجليزية
    -0.73
    CodeAttribute
    -0.72
    ElementException
    -0.68
    testens
    -0.66
    saraba
    -0.65
    脚注の使い方
    -0.65
    POSITIVE LOGITS
     extracts
    0.88
     extract
    0.84
     Extracts
    0.75
     phyto
    0.73
    extract
    0.73
     Extract
    0.70
     extracted
    0.69
     bioactive
    0.68
     extraction
    0.67
     flavon
    0.67
    Activations Density 0.924%

    No Known Activations