© 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. 21055
    Prev
    Next
    INDEX
    Explanations

    statements asserting existence or characteristics of subjects

    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
     épais
    -0.55
     ferdig
    -0.52
    routeProvider
    -0.52
     simply
    -0.52
     ochi
    -0.52
    MLLoader
    -0.51
    邑
    -0.51
     függ
    -0.49
     smě
    -0.49
    andExpect
    -0.48
    POSITIVE LOGITS
    ViewImports
    0.72
    ThroughAttribute
    0.68
     initComponents
    0.65
     propOrder
    0.65
    RectangleBorder
    0.63
    sourceMap
    0.59
    DataAnnotations
    0.58
    DAILY
    0.58
     كومونز
    0.56
    ⓧ
    0.54
    Activations Density 0.046%

    No Known Activations