© 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. 20382
    Prev
    Next
    INDEX
    Explanations

    statements or quotations attributed to experts

    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
    $_['
    -0.69
     Loot
    -0.57
     suprême
    -0.50
    hime
    -0.50
     soigne
    -0.49
     confiscation
    -0.49
     sterility
    -0.48
     kindly
    -0.48
     décid
    -0.48
     Metallurgy
    -0.47
    POSITIVE LOGITS
     Мексичка
    0.88
    Portale
    0.72
    StructEnd
    0.70
    OGND
    0.64
    Identyfik
    0.60
     незавершена
    0.59
    Autoritní
    0.57
     للاسماء
    0.55
    цездатний
    0.55
    propTypes
    0.55
    Activations Density 0.057%

    No Known Activations