© 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. 9964
    Prev
    Next
    INDEX
    Explanations

    references to equations in scientific or mathematical texts

    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
    s
    -0.77
    ities
    -0.62
     Stö
    -0.60
    पया
    -0.59
     fű
    -0.59
    AnchorStyles
    -0.58
    InjectAttribute
    -0.57
    IF
    -0.56
    ses
    -0.56
    Bü
    -0.56
    POSITIVE LOGITS
    eqn
    1.59
     eqn
    1.10
    Eqn
    0.90
     Reforms
    0.82
    Fordítás
    0.81
    enoord
    0.77
    ykjav
    0.76
     صوتيه
    0.76
     wens
    0.76
     Gual
    0.74
    Activations Density 0.001%

    No Known Activations