© 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. 18899
    Prev
    Next
    INDEX
    Explanations

    specific references to privacy-related terms and concepts

    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
    tinyos
    -1.00
    extAlignment
    -0.87
     bezeichneter
    -0.84
    MetaType
    -0.82
    WindowConstants
    -0.81
     propOrder
    -0.81
     AGA
    -0.80
    WithIOException
    -0.80
     Lombard
    -0.79
     ExecuteAsync
    -0.78
    POSITIVE LOGITS
     bij
    1.03
     Bij
    1.02
    Bij
    0.99
     Bei
    0.94
     bei
    0.93
     при
    0.90
    При
    0.88
     При
    0.83
    при
    0.79
    bij
    0.78
    Activations Density 0.004%

    No Known Activations