© 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. 28394
    Prev
    Next
    INDEX
    Explanations

    structures or elements related to data formatting or coding representations

    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
    تقاوى
    -0.91
    findpost
    -0.87
    migrationBuilder
    -0.80
    NOPQRST
    -0.78
     समीक्षाओं
    -0.78
     متعلقه
    -0.76
    IntoConstraints
    -0.75
     eventdata
    -0.73
     ivelany
    -0.72
    Tikang
    -0.71
    POSITIVE LOGITS
    وقف
    0.50
    cils
    0.48
    moiselle
    0.47
    onema
    0.46
    aspx
    0.45
    ampiyon
    0.45
    forKey
    0.44
    izeit
    0.44
     zamiast
    0.44
    anners
    0.43
    Activations Density 0.027%

    No Known Activations