© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    terms related to dog training and enrichment activities

    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
     gái
    -0.56
     تضيفلها
    -0.56
    RUPT
    -0.44
    vamente
    -0.43
    genti
    -0.43
    FECTION
    -0.43
     spos
    -0.42
     {-
    -0.42
    aih
    -0.41
     cortesía
    -0.40
    POSITIVE LOGITS
    TestingModule
    0.85
    Personensuche
    0.74
    principalTable
    0.72
     >::
    0.71
    出版年
    0.70
    참고
    0.70
    /**
    0.70
    RegressionTest
    0.69
    IsMutable
    0.69
    setVerticalGroup
    0.68
    Activations Density 0.065%

    No Known Activations