© 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. 31842
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to statistical laws and processes

    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
     Signalez
    -0.81
    LookAnd
    -0.79
    AnchorTagHelper
    -0.76
     للمعارف
    -0.74
     يتيمه
    -0.74
    migrationBuilder
    -0.74
    AnchorStyles
    -0.71
    ագրություններ
    -0.70
    الحياه
    -0.68
     noDo
    -0.68
    POSITIVE LOGITS
     vectorielle
    0.66
    ennemi
    0.61
     automatiques
    0.57
     fédé
    0.56
     vectorielles
    0.55
     traditionnels
    0.55
    providedIn
    0.54
     nationaux
    0.54
     étoit
    0.53
     loren
    0.53
    Activations Density 0.153%

    No Known Activations