© 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. 12372
    Prev
    Next
    INDEX
    Explanations

    sections that contain references and citations in a structured document

    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
     للمعارف
    -0.71
    ècie
    -0.68
    anyahu
    -0.67
    mybatisplus
    -0.61
    ssysteme
    -0.59
     Connectez
    -0.57
     hObject
    -0.56
    etcode
    -0.55
    enterOuterAlt
    -0.55
     houſe
    -0.55
    POSITIVE LOGITS
    multirow
    0.65
     ExecuteAsync
    0.60
    Acknowledgments
    0.54
     sàng
    0.51
    gebnissen
    0.50
    abestanden
    0.50
     CURIAM
    0.49
    OrBuilder
    0.47
    новништво
    0.47
    жели
    0.47
    Activations Density 0.057%

    No Known Activations