© 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. 9093
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional states and their impact

    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
     AttributeError
    -0.56
    égorie
    -0.53
    يكب
    -0.52
    CastException
    -0.52
    تا
    -0.51
    nase
    -0.50
    ViewFeatures
    -0.49
    tilhe
    -0.47
    rateful
    -0.47
     races
    -0.47
    POSITIVE LOGITS
     BoxDecoration
    0.57
     المعيارى
    0.55
    AccessorTable
    0.54
     StatefulWidget
    0.54
    toMatchSnapshot
    0.53
    windowFixed
    0.53
    anyahu
    0.52
     certainement
    0.52
     بيها
    0.52
     --}}
    0.50
    Activations Density 0.220%

    No Known Activations