© 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. 14998
    Prev
    Next
    INDEX
    Explanations

    phrases indicating findings or conclusions from scientific research

    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
    出版年
    -0.82
    httphttps
    -0.63
    RequestMethod
    -0.56
    miyorum
    -0.54
    pani
    -0.54
     to
    -0.53
    powied
    -0.52
     Steer
    -0.52
    awtextra
    -0.50
     when
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.67
    ThroughAttribute
    0.62
    ய்ய
    0.60
    TypedDataSet
    0.59
    inaldi
    0.57
    HasMaxLength
    0.57
    σιμοποι
    0.57
    XmlEnum
    0.57
    ientôt
    0.56
     للاسماء
    0.56
    Activations Density 0.027%

    No Known Activations