© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26028
    Prev
    Next
    INDEX
    Explanations

    references to organizations and legal frameworks in formal documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Хьажоргаш
    -0.95
     препратки
    -0.69
    parsedMessage
    -0.66
    ГЛА
    -0.66
    Rohy
    -0.63
    aparte
    -0.60
     ostavi
    -0.54
    $__
    -0.54
    الإنجليزية
    -0.53
    blockList
    -0.53
    POSITIVE LOGITS
    клопе
    0.58
    tagHelperRunner
    0.56
    ArgumentParser
    0.52
    TableAdapter
    0.51
    AxisAlignment
    0.50
    ghijklmnop
    0.50
    ClientRect
    0.48
    ruptedException
    0.46
    ElementException
    0.46
     ạ
    0.45
    Activations Density 0.309%

    No Known Activations