© 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. 14937
    Prev
    Next
    INDEX
    Explanations

    references to high-definition (HD) content or technologies

    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
     yyl
    -0.91
    RenderAtEndOf
    -0.85
    BeginContext
    -0.83
     ReSharper
    -0.81
    messageInfo
    -0.80
     препратки
    -0.79
    errHandler
    -0.78
    FormState
    -0.77
     disponibilités
    -0.75
    (!__
    -0.75
    POSITIVE LOGITS
     HD
    1.43
    HD
    1.30
     hd
    1.23
    hd
    1.10
     Hd
    0.88
     BnF
    0.79
     Vergara
    0.77
    Hd
    0.74
     Pires
    0.71
     McKee
    0.71
    Activations Density 0.005%

    No Known Activations