© 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. 23414
    Prev
    Next
    INDEX
    Explanations

    French articles and pronouns

    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
     Theſe
    -0.98
     themſelves
    -0.93
     himſelf
    -0.88
    BibitemShut
    -0.88
     ―――――
    -0.87
     ſind
    -0.85
     iconFacebook
    -0.84
    ſelves
    -0.82
     ſeveral
    -0.82
    DeleteBehavior
    -0.82
    POSITIVE LOGITS
     la
    1.10
     le
    0.77
     M
    0.75
     La
    0.72
     L
    0.69
    BorderFactory
    0.69
    La
    0.68
    員の
    0.66
    la
    0.65
     J
    0.65
    Activations Density 0.073%

    No Known Activations