© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2282
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes, specifically class actions and associated procedures

    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
    AndEndTag
    -0.81
     AssemblyTitle
    -0.68
     InputDecoration
    -0.68
    WriteTagHelper
    -0.65
    .*")]
    -0.65
    ksikon
    -0.63
    !*\
    -0.63
    ContentAsync
    -0.63
     chi̍t
    -0.63
    transQ
    -0.62
    POSITIVE LOGITS
     Masses
    0.58
     mass
    0.54
    Thousands
    0.54
    ukų
    0.54
     Minne
    0.49
     détail
    0.49
     millions
    0.48
     numé
    0.48
     hundreds
    0.48
     Bondi
    0.48
    Activations Density 0.032%

    No Known Activations