© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23346
    Prev
    Next
    INDEX
    Explanations

    specific combinations of letters or phonemes related to picking events in a probabilistic context

    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
    Negative Logits
    ThroughAttribute
    -0.81
    StructEnd
    -0.71
    tangentMode
    -0.60
     StatefulWidget
    -0.57
    !*\
    -0.56
     fieldNum
    -0.56
    WaitGroup
    -0.56
    fastjson
    -0.55
    россий
    -0.54
     jsPsych
    -0.54
    POSITIVE LOGITS
     الحره
    0.54
    Див
    0.53
     Electrical
    0.49
    willReturn
    0.49
    WebVitals
    0.49
     electrical
    0.48
     motocic
    0.48
     Schrö
    0.46
    kelijke
    0.45
     Schot
    0.45
    Activations Density 0.006%

    No Known Activations