© 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. 20364
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court orders and decisions

    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
    AndroidJUnit
    -0.68
     الاطلاع
    -0.62
    UnknownFieldSet
    -0.61
     Diarsipkan
    -0.60
    StandardCharsets
    -0.58
     NSError
    -0.57
    sidemargin
    -0.57
    zelle
    -0.56
     Ellos
    -0.55
    kloped
    -0.55
    POSITIVE LOGITS
     ويكيميديا
    0.53
    routeProvider
    0.52
    مصادر
    0.49
    이터
    0.47
     createState
    0.47
    csol
    0.47
    AndEndTag
    0.45
     ORDERED
    0.44
     getchar
    0.42
    IsPostBack
    0.42
    Activations Density 0.009%

    No Known Activations