© 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. 22-RES-MATRYOSHKA-DC
    7. 1478
    Prev
    Next
    INDEX
    Explanations

    articles that end with some kind of mark indicating more information is available

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     JpaRepository
    -0.56
    ---*/
    -0.56
     ISNI
    -0.56
     $__
    -0.55
    الحياه
    -0.55
    IndentedString
    -0.49
    writeFieldEnd
    -0.48
    }")
    -0.47
     }}"></
    -0.47
     getItemId
    -0.47
    POSITIVE LOGITS
     How
    0.82
     Welcome
    0.79
     Learn
    0.75
     Explore
    0.73
     Read
    0.73
     Hello
    0.71
     View
    0.71
     Visit
    0.70
     Share
    0.69
     What
    0.68
    Activations Density 1.524%

    No Known Activations