© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1767
    Prev
    Next
    INDEX
    Explanations

    references to figures or supplementary materials in scientific publications

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CiNii
    -0.62
     vectorielles
    -0.61
     Мексичка
    -0.56
    Modèle
    -0.55
     оригіналу
    -0.54
     الوطنيه
    -0.54
     
    -0.54
    theoremstyle
    -0.54
    ότη
    -0.54
    ьаж
    -0.53
    POSITIVE LOGITS
    Figs
    0.87
    Fig
    0.79
     Figs
    0.77
     Fig
    0.75
     figs
    0.62
     fig
    0.60
    fig
    0.59
    WaitGroup
    0.57
     Aug
    0.54
    usr
    0.53
    Activations Density 0.181%

    No Known Activations