© 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. 29317
    Prev
    Next
    INDEX
    Explanations

    content related to legal or copyright information

    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
     '\\;'
    -0.74
    astéroïdes
    -0.66
    GEBURTSDATUM
    -0.66
    QMetaType
    -0.64
    évaluateur
    -0.61
    ItemBackground
    -0.61
     resourceCulture
    -0.60
     الحره
    -0.57
     مرئيه
    -0.57
    Przypisy
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.81
    vans
    0.58
    notice
    0.57
     NOTICE
    0.56
    Notices
    0.53
     notices
    0.53
     annonce
    0.53
    Notice
    0.52
     claim
    0.52
     Notice
    0.51
    Activations Density 0.002%

    No Known Activations