© 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. 10732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need to evaluate or reconsider a legal decision or argument

    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
     فق
    -0.57
    ########.
    -0.55
     transfieras
    -0.53
    AutoresizingMask
    -0.51
    shared
    -0.51
     illet
    -0.49
     shared
    -0.48
    zwald
    -0.48
    äischen
    -0.48
     المع
    -0.48
    POSITIVE LOGITS
    omitempty
    0.65
     kaynağından
    0.60
    цездатний
    0.59
    下载附件
    0.58
    日閲覧
    0.56
    PageModule
    0.55
    SceneManagement
    0.52
    tonsoft
    0.52
     रेटिंग
    0.51
     AssemblyTitle
    0.50
    Activations Density 0.023%

    No Known Activations