© 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. 29336
    Prev
    Next
    INDEX
    Explanations

    terms related to process and system controls

    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
     ADB
    -0.46
     grà
    -0.44
     Bede
    -0.44
     Trafalgar
    -0.43
     Humber
    -0.42
    pot
    -0.41
    aci
    -0.41
    höhe
    -0.41
    CCL
    -0.40
     Toda
    -0.40
    POSITIVE LOGITS
    Démographie
    0.78
    NameInMap
    0.66
     jadx
    0.66
    ittarius
    0.62
     protoimpl
    0.61
    tvguidetime
    0.60
    letics
    0.60
    rijfs
    0.59
     propOrder
    0.59
    yorsunuz
    0.58
    Activations Density 1.669%

    No Known Activations