© 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. 23328
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical expressions or equations involving brackets

    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
     itſelf
    -1.14
     myſelf
    -1.05
     Jefus
    -1.04
     Efq
    -1.04
     himſelf
    -1.03
     themſelves
    -1.02
     ſeveral
    -0.96
     pleaſure
    -0.94
     Houſe
    -0.92
     Majefty
    -0.91
    POSITIVE LOGITS
    itní
    0.59
     miele
    0.56
    e
    0.54
     lí
    0.51
     BoxFit
    0.51
     labios
    0.50
     :
    0.49
     égard
    0.49
     chuyên
    0.48
    ղ
    0.48
    Activations Density 0.002%

    No Known Activations