© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and diagrams

    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
     للمعارف
    -0.78
    __':
    -0.67
     >=",
    -0.65
    WidgetItem
    -0.64
     ErrIntOverflow
    -0.62
    grande
    -0.61
    tagext
    -0.61
    autoreleasepool
    -0.61
    rawDesc
    -0.60
    __":
    -0.60
    POSITIVE LOGITS
     map
    1.06
     Map
    0.91
    Map
    0.90
    map
    0.88
     maps
    0.87
     Maps
    0.82
     mapping
    0.82
    Maps
    0.74
    maps
    0.74
     mapas
    0.72
    Activations Density 0.832%

    No Known Activations