© 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. 17687
    Prev
    Next
    INDEX
    Explanations

    specific types of programming constructs and their attributes

    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
    SequentialGroup
    -1.15
    Vidite
    -0.95
     EconPapers
    -0.84
     Paglinawan
    -0.81
     NgModule
    -0.79
     <",
    -0.75
    Xna
    -0.74
     CommonModule
    -0.74
    providedIn
    -0.73
     continúas
    -0.73
    POSITIVE LOGITS
     ģ
    0.52
     gyakor
    0.47
     sauvages
    0.47
     acestui
    0.47
     massima
    0.46
     proprement
    0.45
     Crédito
    0.45
     resistenza
    0.44
     virš
    0.43
     tromper
    0.42
    Activations Density 0.011%

    No Known Activations