© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5485
    Prev
    Next
    INDEX
    Explanations

    references to hardware register masks

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secret
    -0.72
     Segovia
    -0.66
     SECRET
    -0.64
    secret
    -0.63
    Secret
    -0.61
    ATTRIBUTE
    -0.61
     Guildford
    -0.60
     plaintext
    -0.59
    SECRET
    -0.58
     tajem
    -0.58
    POSITIVE LOGITS
     mask
    3.36
    mask
    3.23
     Mask
    3.19
    Mask
    3.16
     masks
    2.92
     MASK
    2.84
     Masks
    2.66
    masks
    2.58
    MASK
    2.42
    Masks
    2.34
    Activations Density 0.023%

    No Known Activations