© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    exclamations and expressions of surprise or realization

    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
    HttpEntity
    -0.59
     Credo
    -0.57
     Andover
    -0.54
    Seriously
    -0.54
     Exactly
    -0.53
     africaine
    -0.53
     كمان
    -0.53
     COMPR
    -0.52
     Wheeling
    -0.52
     całym
    -0.52
    POSITIVE LOGITS
    verwijspagina
    0.90
    Personendaten
    0.74
     Baillargeon
    0.66
    Sucesor
    0.66
    rungsseite
    0.64
     kasarigan
    0.63
    oredCriteria
    0.63
     kaynağından
    0.61
    ]--;
    0.60
    .*")]
    0.57
    Activations Density 0.009%

    No Known Activations