© 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. 22787
    Prev
    Next
    INDEX
    Explanations

    negative judgments about behavior or actions

    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
    NameInMap
    -0.49
     تحد
    -0.47
     sund
    -0.47
    hten
    -0.46
    PageContext
    -0.46
     change
    -0.45
     gaz
    -0.45
     prove
    -0.45
    лам
    -0.45
    ?
    -0.44
    POSITIVE LOGITS
     dignité
    0.64
     Efq
    0.64
     primaire
    0.60
    原始内容存档于
    0.59
    μως
    0.59
     chré
    0.59
     honte
    0.59
    例文帳に追加
    0.59
     Shakspeare
    0.58
     dàng
    0.57
    Activations Density 0.117%

    No Known Activations