© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    quotation marks, indicating dialogue or quoted speech

    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
    Portale
    -0.94
    脚注の使い方
    -0.86
    $.
    -0.85
     насељу
    -0.85
    )”.
    -0.83
     betweenstory
    -0.81
     ')
    -0.78
    kháu
    -0.78
     ")
    -0.77
    expandindo
    -0.76
    POSITIVE LOGITS
    <eos>
    0.51
     certainly
    0.51
    if
    0.50
    Pro
    0.49
    '
    0.47
     gepubliceerd
    0.46
     because
    0.46
    w
    0.46
    ↵↵↵
    0.46
    yadh
    0.46
    Activations Density 0.001%

    No Known Activations