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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19594
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to procedural directives and mandates

    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
    CDATA
    -0.56
    "]));
    -0.55
    กัน
    -0.54
     selam
    -0.53
    hug
    -0.51
     كومونز
    -0.51
    bited
    -0.51
    mailto
    -0.50
    ритори
    -0.49
     memoized
    -0.49
    POSITIVE LOGITS
    tagext
    0.63
     diminta
    0.57
    didSet
    0.53
    GOTREF
    0.52
    ास्त
    0.52
    도록
    0.52
     recommandons
    0.51
    fromnode
    0.50
     fisica
    0.50
    Ecotoxicity
    0.49
    Activations Density 0.192%

    No Known Activations