© 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. 0-RES-MATRYOSHKA-DC
    7. 15961
    Prev
    Next
    INDEX
    Explanations

    references to physical structures used as barriers or barriers-like components

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    gate
    -0.83
     дописавши
    -0.78
     BorderRadius
    -0.71
     StatefulWidget
    -0.70
     OkHttpClient
    -0.66
    Gate
    -0.64
     nahilalakip
    -0.62
    شهاد
    -0.61
    ")]
    -0.61
    BASEPATH
    -0.58
    POSITIVE LOGITS
     gates
    2.16
    gates
    0.96
     puertas
    0.73
     doors
    0.71
     gated
    0.69
    ModelAdmin
    0.65
     portes
    0.65
     governors
    0.58
    principalTable
    0.57
     shutters
    0.56
    Activations Density 0.001%

    No Known Activations