© 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. 23431
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and notation related to equations and structures

    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
    -0.96
    tanleria
    -0.79
    WithIOException
    -0.79
     Roskov
    -0.75
    Personendaten
    -0.73
     resourceCulture
    -0.71
    حياتها
    -0.71
    DeleteBehavior
    -0.68
    Šaltiniai
    -0.67
    postmedia
    -0.67
    POSITIVE LOGITS
    arna
    0.47
    ForType
    0.42
    bilder
    0.41
     كومونز
    0.41
     future
    0.41
    ylim
    0.40
     будущего
    0.40
     bore
    0.40
     futurs
    0.40
    nem
    0.40
    Activations Density 0.093%

    No Known Activations