© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and arguments related to trial court decisions and evidentiary issues

    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
    ChildScrollView
    -0.83
    PerformLayout
    -0.72
    istoitu
    -0.65
    MemoryWarning
    -0.63
    fjspx
    -0.61
     Exacts
    -0.59
    脚注の使い方
    -0.59
    MessageTagHelper
    -0.58
     محفوظة
    -0.56
    indd
    -0.56
    POSITIVE LOGITS
     otomatig
    0.62
     ddelweddau
    0.55
    gulation
    0.53
    ersburg
    0.50
     Chriftian
    0.48
     indepen
    0.48
     initially
    0.47
    mical
    0.47
    rophoresis
    0.47
     sice
    0.46
    Activations Density 0.093%

    No Known Activations