© 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. 20433
    Prev
    Next
    INDEX
    Explanations

    queries or suggestions related to changing or simplifying processes

    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
     definitely
    -0.51
    بوابة
    -0.50
     never
    -0.48
     Never
    -0.48
     lo
    -0.46
     certainly
    -0.44
     apro
    -0.44
     future
    -0.43
     zal
    -0.43
     أجل
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.75
    complexContent
    0.74
     autorytatywna
    0.73
     Cæsar
    0.71
     Chriftian
    0.70
     fubject
    0.69
     mères
    0.67
     stället
    0.67
     itſelf
    0.67
     Reſ
    0.66
    Activations Density 0.074%

    No Known Activations