© 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. 22983
    Prev
    Next
    INDEX
    Explanations

    structured data definitions and configurations

    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
     (°
    -0.52
    enderror
    -0.52
     समीक्षाओं
    -0.52
    Tikang
    -0.49
    acabana
    -0.48
    OCCURRED
    -0.48
    icordia
    -0.47
    ثيق
    -0.47
     muck
    -0.46
    epiece
    -0.45
    POSITIVE LOGITS
    posedge
    0.79
    awtextra
    0.71
    setVerticalGroup
    0.68
    Obrázky
    0.62
    Referencies
    0.61
    kháu
    0.58
    CloseOperation
    0.57
     geometr
    0.57
    InSection
    0.56
    hyrchwyd
    0.56
    Activations Density 0.062%

    No Known Activations