© 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. 9816
    Prev
    Next
    INDEX
    Explanations

    arrays and matrix indices used in programming, particularly in the context of data manipulation or visualization

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gouttes
    -0.82
     nôtre
    -0.73
    djangoproject
    -0.70
    empêcher
    -0.69
     tombé
    -0.67
     Hov
    -0.65
     télécharge
    -0.65
     biß
    -0.65
     Efq
    -0.65
    doj
    -0.64
    POSITIVE LOGITS
    [:,
    0.97
    (:,
    0.84
     CWE
    0.59
    Kanpo
    0.56
     [[
    0.53
     initComponents
    0.52
    kkue
    0.50
    [[
    0.49
     means
    0.49
    
    0.49
    Activations Density 0.011%

    No Known Activations