© 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. 30662
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to authority and permissions

    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
    MemoryWarning
    -0.73
    ergies
    -0.68
    ruptcy
    -0.65
    ResumeLayout
    -0.63
     AssemblyCompany
    -0.62
    UNDLE
    -0.62
    serum
    -0.60
    IntentFilter
    -0.60
     jLabel
    -0.58
    konos
    -0.58
    POSITIVE LOGITS
     EconPapers
    0.59
     auto
    0.54
    Auto
    0.52
     Auto
    0.52
    发表于
    0.49
    auto
    0.47
    DotNetBar
    0.47
    ngdoc
    0.45
     Heraus
    0.45
     nghề
    0.44
    Activations Density 0.131%

    No Known Activations