© 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. 10083
    Prev
    Next
    INDEX
    Explanations

    terms related to inferences and their evidentiary support in legal contexts

    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
     wetter
    -0.56
    цепт
    -0.54
    SECTOR
    -0.54
    Попис
    -0.52
     uſ
    -0.52
    Ecotoxicity
    -0.51
     Stripes
    -0.50
    ContentAsync
    -0.50
     definição
    -0.49
    BRIEF
    -0.48
    POSITIVE LOGITS
     المعيارى
    0.84
    enumii
    0.71
    PYX
    0.66
    AxisAlignment
    0.63
    PreferredItem
    0.63
     متعلقه
    0.62
    CloseOperation
    0.62
    verifyException
    0.62
    :+:
    0.61
    saraba
    0.61
    Activations Density 0.002%

    No Known Activations