© 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. 23391
    Prev
    Next
    INDEX
    Explanations

    key moments of physical interaction and pauses in dialogue

    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
    GEBURTSDATUM
    -0.79
    AutoScale
    -0.79
     whoſe
    -0.79
     Efq
    -0.79
     مشين
    -0.78
     uſed
    -0.78
    WebVitals
    -0.77
     Jefus
    -0.77
     OFDb
    -0.77
     itſelf
    -0.75
    POSITIVE LOGITS
     stop
    0.70
     STOP
    0.68
     Stop
    0.66
     stops
    0.65
    Stops
    0.57
    STOP
    0.56
    Stop
    0.56
     Stops
    0.54
     stopping
    0.53
    stop
    0.51
    Activations Density 0.039%

    No Known Activations