© 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. 14882
    Prev
    Next
    INDEX
    Explanations

    narratives about travel experiences and family connections

    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
    sproble
    -0.69
    +#+#
    -0.62
    HandlerContext
    -0.59
    OpenHelper
    -0.57
    WithIOException
    -0.56
     Soud
    -0.55
     Adoption
    -0.54
    MLLoader
    -0.53
     chng
    -0.52
    ScopeManager
    -0.52
    POSITIVE LOGITS
     travel
    0.90
     itinerary
    0.80
    travel
    0.78
     Travel
    0.76
     itineraries
    0.73
    Travel
    0.70
     سفر
    0.68
     TRAVEL
    0.64
     travelled
    0.63
     traveller
    0.63
    Activations Density 0.174%

    No Known Activations