© 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. 22851
    Prev
    Next
    INDEX
    Explanations

    themes related to human experiences and societal issues

    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
    jmniej
    -0.70
     Wikispecies
    -0.64
    Personendaten
    -0.64
     Савезне
    -0.63
    irmingham
    -0.62
     ویکی‌پدیا
    -0.59
     resourceCulture
    -0.57
    HtmlAttribute
    -0.57
     Pologne
    -0.57
    Brainz
    -0.57
    POSITIVE LOGITS
     ancient
    0.54
    ancient
    0.52
    +#+#
    0.50
     básico
    0.50
     moderno
    0.49
    Sore
    0.48
     Ancient
    0.47
    Ancient
    0.46
     vintage
    0.45
     traditionnelle
    0.45
    Activations Density 0.139%

    No Known Activations