© 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. 12-RES-MATRYOSHKA-DC
    7. 11178
    Prev
    Next
    INDEX
    Explanations

    references to data availability and citation formats in research 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
     שוליים
    -0.70
    بوابة
    -0.69
    RectangleBorder
    -0.62
    Odkazy
    -0.60
     AssemblyCulture
    -0.60
    databind
    -0.59
    lanzen
    -0.57
    createTextNode
    -0.57
     الحره
    -0.56
    PyExc
    -0.56
    POSITIVE LOGITS
    DebuggerNonUser
    0.52
     Nebel
    0.50
     protoimpl
    0.48
    /#{
    0.48
    sigue
    0.47
    niño
    0.47
    suff
    0.47
    "/",
    0.47
    تقاوى
    0.46
    postmedia
    0.46
    Activations Density 0.001%

    No Known Activations