© 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. 14550
    Prev
    Next
    INDEX
    Explanations

    references to figures in scientific documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.94
    Искәрмәләр
    -0.79
     unknownFields
    -0.74
     MATE
    -0.73
     VGA
    -0.72
    ЧИТА
    -0.72
     pory
    -0.71
     kasarigan
    -0.70
    bibinfo
    -0.69
    romos
    -0.69
    POSITIVE LOGITS
    Fig
    0.94
     تضيفلها
    0.89
     Fig
    0.78
    addGap
    0.73
    rg
    0.70
    httphttps
    0.70
    rs
    0.69
     Figs
    0.66
    in
    0.65
    Figs
    0.65
    Activations Density 0.006%

    No Known Activations