© 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. 28038
    Prev
    Next
    INDEX
    Explanations

    code syntax related to function or method calls

    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
     CreateTagHelper
    -0.89
    ^(@)
    -0.77
    ScopeManager
    -0.70
     nahilalakip
    -0.70
     snippetHide
    -0.68
     surla
    -0.68
     AssemblyCulture
    -0.67
     viện
    -0.67
     Waray
    -0.67
     voud
    -0.66
    POSITIVE LOGITS
     Nah
    0.53
    <eos>
    0.50
    ↵
    0.50
     us
    0.49
    ↵↵
    0.47
    שר
    0.47
    Nah
    0.44
     The
    0.44
     plus
    0.44
    íí
    0.44
    Activations Density 0.193%

    No Known Activations