© 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. 11226
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics presented in the text

    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
    ChildScrollView
    -0.90
    aarrggbb
    -0.90
    jsonwebtoken
    -0.88
    InitVars
    -0.79
    '])){
    -0.77
    asteroide
    -0.73
    راقي
    -0.72
     Palin
    -0.72
    '){
    -0.71
    issner
    -0.71
    POSITIVE LOGITS
     تضيفلها
    0.69
    o
    0.68
    W
    0.62
    P
    0.62
    ільки
    0.61
    O
    0.60
    aster
    0.58
    e
    0.57
    ſelf
    0.56
    i
    0.56
    Activations Density 0.011%

    No Known Activations