© 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. 10086
    Prev
    Next
    INDEX
    Explanations

    references to the programming language Ember.js

    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
    ">{{$
    -0.70
    alleye
    -0.68
    TacToe
    -0.63
    tahui
    -0.63
    GenerationType
    -0.60
    GoogleMap
    -0.60
    hér
    -0.59
     Pits
    -0.59
     kjem
    -0.57
     Chic
    -0.56
    POSITIVE LOGITS
     Ember
    1.99
    ember
    1.75
    Ember
    1.72
     ember
    1.44
     embers
    0.93
     تضيفلها
    0.90
    :✨
    0.84
    EMBER
    0.77
    Tikang
    0.77
    contentLoaded
    0.74
    Activations Density 0.001%

    No Known Activations