© 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. 20517
    Prev
    Next
    INDEX
    Explanations

    references to the code editor Vim and its configuration

    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
     crossorigin
    -0.62
     NSCoder
    -0.60
    openqa
    -0.57
    enumi
    -0.57
    Portale
    -0.57
    addCriterion
    -0.53
    TokenName
    -0.52
    ing
    -0.51
    AddTagHelper
    -0.51
     onCreateView
    -0.50
    POSITIVE LOGITS
     Vim
    1.05
    macs
    1.00
    Vim
    1.00
     Lisp
    0.92
     vim
    0.84
     ajuns
    0.71
    vim
    0.67
     AttributeSet
    0.65
     klubben
    0.61
    værende
    0.59
    Activations Density 0.006%

    No Known Activations