© 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. 13864
    Prev
    Next
    INDEX
    Explanations

    lines or sections indicating significant numerical or data results

    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
     Lise
    -0.95
     Lumia
    -0.94
     Duffy
    -0.88
    izmu
    -0.80
     Levine
    -0.79
    endpush
    -0.79
     Nye
    -0.75
    Lise
    -0.75
     Wulf
    -0.74
     Stel
    -0.73
    POSITIVE LOGITS
    expandindo
    0.95
    ------------
    0.86
     greateſt
    0.83
     ---------
    0.83
     Paglinawan
    0.81
     preſent
    0.80
     laſt
    0.74
    en
    0.73
     ſtate
    0.73
     perſon
    0.72
    Activations Density 0.015%

    No Known Activations