© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    references to numerical ranges or specifications

    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
     Nutt
    -0.84
     Witkin
    -0.84
     Eleventh
    -0.77
     Mooney
    -0.74
    Сюжет
    -0.73
    letus
    -0.72
     CREDITS
    -0.72
    Искәрмәләр
    -0.71
     UITableViewCell
    -0.71
     bookId
    -0.71
    POSITIVE LOGITS
     ranges
    1.80
     range
    1.77
     Range
    1.74
     RANGE
    1.63
    range
    1.55
    Range
    1.55
    ranges
    1.55
     Ranges
    1.54
    RANGE
    1.51
    Ranges
    1.50
    Activations Density 0.129%

    No Known Activations