© 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. 24861
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and packages

    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
     CWE
    -0.69
    
    -0.68
     MainAxisSize
    -0.65
    RenderAtEndOf
    -0.65
    migrationBuilder
    -0.65
     оригіналу
    -0.65
    SharedDtor
    -0.63
    AddTagHelper
    -0.61
    WriteAttribute
    -0.61
     MonoBehaviour
    -0.60
    POSITIVE LOGITS
    amssymb
    0.43
     [*]
    0.42
    heets
    0.41
    kies
    0.41
    יוחד
    0.41
     illimit
    0.40
     décédé
    0.40
    ılmıştır
    0.40
     hâte
    0.39
     cuar
    0.39
    Activations Density 0.005%

    No Known Activations