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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13867
    Prev
    Next
    INDEX
    Explanations

    code snippets related to reading and processing filesystem superblock structures

    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
     blocks
    -1.36
     Blocks
    -1.26
    المناصب
    -0.85
    CppMethod
    -0.82
    sizeCache
    -0.77
    Blocks
    -0.77
    ttemberg
    -0.76
    üyada
    -0.76
    قایناق‌لار
    -0.76
    లాలు
    -0.74
    POSITIVE LOGITS
    block
    1.43
    richTextPanel
    0.54
    buck
    0.54
     Crown
    0.48
    ec
    0.48
     zar
    0.47
    crown
    0.46
    toggler
    0.46
    book
    0.45
     besar
    0.45
    Activations Density 0.004%

    No Known Activations