© 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. 22-RES-MATRYOSHKA-DC
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    references to equations or sections

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    <!--[
    -0.69
    Bibliograf
    -0.56
     ту
    -0.54
    Autoritní
    -0.47
    ticulate
    -0.47
    ANTIC
    -0.47
     einsetzen
    -0.46
     "",
    -0.45
    forbes
    -0.45
     reinforced
    -0.45
    POSITIVE LOGITS
    enumi
    0.73
    IsMutable
    0.72
    ьаж
    0.72
    homonymie
    0.69
    OrNil
    0.69
    Hentet
    0.69
     المعيارى
    0.68
    躇
    0.64
    出版年
    0.63
    itespace
    0.62
    Activations Density 0.024%

    No Known Activations