© 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. 8484
    Prev
    Next
    INDEX
    Explanations

    sentences containing legal terminology and references to actions or requests 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
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.80
     للاسماء
    -0.72
     HttpNotFound
    -0.72
     gyhoeddwyd
    -0.70
    حياتها
    -0.69
     entanto
    -0.68
    ftagPool
    -0.65
    UrlResolution
    -0.63
    WebServlet
    -0.63
    UTERS
    -0.62
    POSITIVE LOGITS
     nữa
    0.61
     too
    0.57
    こちらも
    0.56
    Билгалдахарш
    0.56
    too
    0.54
     тоже
    0.52
    についても
    0.47
    ことも
    0.46
     ebenfalls
    0.45
     naman
    0.45
    Activations Density 0.521%

    No Known Activations