© 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. 13748
    Prev
    Next
    INDEX
    Explanations

    specific references to local events and geographical context

    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
     ExecuteAsync
    -1.00
     مرئيه
    -0.82
     himo
    -0.81
     المعيارى
    -0.81
    Datuak
    -0.78
    IUrlHelper
    -0.77
    bootstrapcdn
    -0.76
     Biôgrafia
    -0.73
     tartalomajánló
    -0.71
    GEBURTSDATUM
    -0.70
    POSITIVE LOGITS
     local
    0.78
     locally
    0.71
    local
    0.70
    locally
    0.66
    Local
    0.65
    本地
    0.60
    Locally
    0.60
     Local
    0.58
     LOCAL
    0.56
     lokal
    0.55
    Activations Density 1.036%

    No Known Activations