© 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. 15002
    Prev
    Next
    INDEX
    Explanations

    instances of Python module import statements

    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
    AndEndTag
    -0.69
    endregion
    -0.60
    Xna
    -0.60
     المعيارى
    -0.60
    ArgsConstructor
    -0.59
    ngOnInit
    -0.57
     OnInit
    -0.54
    ulipas
    -0.54
     AutoMapper
    -0.52
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
    dflare
    0.64
     Sadler
    0.63
     Abonnez
    0.62
    Depot
    0.61
     Partagez
    0.61
    ėmis
    0.59
    RegressionTest
    0.59
     Shooter
    0.59
    Controllo
    0.57
     Sorbonne
    0.56
    Activations Density 0.004%

    No Known Activations