© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    references to structured data formats or specifications related to technology or engineering

    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
     Nauk
    -0.60
    principalColumn
    -0.57
    createComponent
    -0.52
    Jeografia
    -0.48
     warm
    -0.47
    umumkan
    -0.47
    สัง
    -0.47
    co
    -0.46
    !*\
    -0.45
     œil
    -0.45
    POSITIVE LOGITS
    Datuak
    0.77
    Personendaten
    0.70
     виправивши
    0.62
     Bins
    0.57
     beginnetje
    0.56
     SafeMath
    0.55
    Filmographie
    0.54
    crollView
    0.54
     DMG
    0.54
     MenuView
    0.54
    Activations Density 0.008%

    No Known Activations