© 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. 20171
    Prev
    Next
    INDEX
    Explanations

    code comments or documentation style elements

    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
    AsUp
    -0.67
     وتسجيلات
    -0.52
    ValueStyle
    -0.50
    endpush
    -0.49
    newblock
    -0.48
     Reece
    -0.48
    parsedMessage
    -0.48
     bust
    -0.47
     kasarigan
    -0.46
    vase
    -0.46
    POSITIVE LOGITS
     himſelf
    0.76
    IUrlHelper
    0.73
     Theſe
    0.73
    iastical
    0.68
    äch
    0.67
     发表于
    0.67
     Monfieur
    0.66
    ParseTree
    0.66
    ]--;
    0.65
     odeur
    0.65
    Activations Density 0.019%

    No Known Activations