© 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. 25788
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and judicial contexts, particularly focusing on accountability and public trust

    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
    Not in Any Lists

    No Comments

    Negative Logits
    )|^{
    -0.66
    )}]{
    -0.66
     Audiodateien
    -0.65
    bibfield
    -0.64
     célè
    -0.63
    bibinfo
    -0.63
    }-${
    -0.63
     
    -0.61
    ambiguation
    -0.60
    لكتر
    -0.60
    POSITIVE LOGITS
    الحياه
    0.55
     समीक्षक
    0.51
     Italijani
    0.51
     referrerpolicy
    0.50
     دیکھیے
    0.50
    DebuggerStep
    0.49
     OMITBAD
    0.49
    RectangleBorder
    0.48
    хьтан
    0.48
     pinulongan
    0.47
    Activations Density 1.529%

    No Known Activations