© 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. 30789
    Prev
    Next
    INDEX
    Explanations

    financial penalties and restitution amounts associated with legal cases

    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
     économies
    -0.57
     долго
    -0.52
     neceff
    -0.51
     LUMP
    -0.50
    ulatum
    -0.48
     exchange
    -0.48
    žin
    -0.48
     spent
    -0.47
     pleaſure
    -0.47
     ArrayAdapter
    -0.47
    POSITIVE LOGITS
    HostException
    0.70
    зулта
    0.66
    IContainer
    0.60
     fined
    0.60
     NUKAT
    0.58
     فريبيس
    0.57
    存于互联网档案馆
    0.54
    -------
    0.54
    ClientRect
    0.54
    دانشنامهٔ
    0.54
    Activations Density 0.037%

    No Known Activations