© 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. 0-RES-MATRYOSHKA-DC
    7. 12881
    Prev
    Next
    INDEX
    Explanations

    references to covering or shielding objects or concepts

    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
    Халык
    -0.52
    StatusBadRequest
    -0.44
    ونه
    -0.42
     SWT
    -0.42
    offsetHeight
    -0.42
    gms
    -0.41
    tna
    -0.41
     participants
    -0.41
     وانت
    -0.40
     WARRANTIES
    -0.40
    POSITIVE LOGITS
    cover
    2.02
    COVER
    1.15
    Cover
    1.09
    covering
    1.01
    covers
    0.95
    discover
    0.94
     Discover
    0.85
    discovered
    0.84
    covered
    0.84
    discovery
    0.82
    Activations Density 0.001%

    No Known Activations