© 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. 20267
    Prev
    Next
    INDEX
    Explanations

    references to major technology companies and their competitive dynamics

    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
     network
    -0.67
     brand
    -0.55
    GetType
    -0.52
     cref
    -0.52
     networks
    -0.50
     uska
    -0.48
     ży
    -0.47
     MaterialApp
    -0.47
    network
    -0.46
    vle
    -0.46
    POSITIVE LOGITS
    ViewImports
    0.98
     bénévoles
    0.75
     organisiert
    0.69
    énario
    0.68
     pesante
    0.64
    RenderAtEndOf
    0.64
     ouvriers
    0.64
     manutenzione
    0.64
    Personendaten
    0.63
     trekken
    0.62
    Activations Density 0.017%

    No Known Activations