© 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. 32340
    Prev
    Next
    INDEX
    Explanations

    references to Semitic languages and their associated terms

    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
     Par
    -0.65
    gh
    -0.64
     Per
    -0.64
    on
    -0.60
    <eos>
    -0.59
     –
    -0.58
    zz
    -0.57
     Ver
    -0.57
     D
    -0.56
    T
    -0.56
    POSITIVE LOGITS
     Hebrew
    1.26
    Hebrew
    1.20
    RenderAtEndOf
    1.16
     Hebrews
    1.09
     myſelf
    1.03
     Theſe
    0.96
     ་་
    0.96
     Malayalam
    0.91
    Hebrews
    0.90
    engertian
    0.89
    Activations Density 0.003%

    No Known Activations