© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5401
    Prev
    Next
    INDEX
    Explanations

    terms related to data retrieval and access operations

    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
    vised
    -0.50
     rest
    -0.48
    ouna
    -0.47
     led
    -0.45
     Dunkel
    -0.44
     re
    -0.43
     play
    -0.43
    ัตว์
    -0.42
     Red
    -0.41
     above
    -0.41
    POSITIVE LOGITS
     snatched
    1.09
     Extraction
    1.00
     extraction
    0.99
     grabbed
    0.95
     Retrieval
    0.95
     extracted
    0.94
     FetchType
    0.94
     Harvesting
    0.93
    extraction
    0.92
     retrieves
    0.91
    Activations Density 0.705%

    No Known Activations