© 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. 31265
    Prev
    Next
    INDEX
    Explanations

    keywords that indicate access modifiers in code, specifically "public," "protected," and "private."

    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
     invokingState
    -0.78
     kasarigan
    -0.77
    <tfoot>
    -0.74
    はじめに
    -0.73
    ftagPool
    -0.71
    rungsseite
    -0.70
    UVWXYZ
    -0.69
    sidemargin
    -0.68
    AxisAlignment
    -0.65
    IsMutable
    -0.64
    POSITIVE LOGITS
    tagHelper
    0.60
     Collo
    0.59
    consulté
    0.57
    Клуб
    0.54
    conta
    0.54
    quine
    0.54
     nhật
    0.53
    Liên
    0.52
    Busch
    0.52
    Sede
    0.52
    Activations Density 0.004%

    No Known Activations