© 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. 2-RES-MATRYOSHKA-DC
    7. 2628
    Prev
    Next
    INDEX
    Explanations

    references to topics related to healthcare professionals and studies involving their knowledge, attitudes, or implementation of safety cultures

    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
    Negative Logits
     <=",
    -0.69
    RTEE
    -0.66
    Rohy
    -0.66
    Autoritní
    -0.64
    Portale
    -0.61
    OGND
    -0.61
     الحره
    -0.61
    +#+#
    -0.59
    رشف
    -0.57
    ikbaar
    -0.56
    POSITIVE LOGITS
     unknownFields
    0.54
    NOPQRST
    0.48
    Stateless
    0.46
    EDEFAULT
    0.45
    "?>
    0.45
     مشين
    0.43
    rural
    0.42
     nakalista
    0.42
    TypeDef
    0.41
     onBind
    0.41
    Activations Density 2.385%

    No Known Activations