© 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. 12760
    Prev
    Next
    INDEX
    Explanations

    references to the Dojo toolkit and its modules in JavaScript code

    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
     “
    -0.62
     ‘
    -0.54
     N
    -0.53
    اء
    -0.53
     a
    -0.52
     A
    -0.52
     po
    -0.52
     U
    -0.51
     
    -0.51
     Co
    -0.50
    POSITIVE LOGITS
    dojo
    1.38
     houſe
    1.27
     itſelf
    1.21
     Efq
    1.18
     Jefus
    1.17
     ſtate
    1.13
     myſelf
    1.13
     Majefty
    1.12
     pleaſure
    1.12
     Houſe
    1.11
    Activations Density 0.015%

    No Known Activations