© 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. 14998
    Prev
    Next
    INDEX
    Explanations

    the presence of venous structures or venous-related components

    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
    帖最后由
    -0.71
    fillType
    -0.65
    SpringBootTest
    -0.63
    PyExc
    -0.63
    kháu
    -0.61
    léans
    -0.60
    RTRS
    -0.57
     EClass
    -0.55
     ๆ
    -0.54
     MyBatis
    -0.54
    POSITIVE LOGITS
     exchanger
    1.23
    ayan
    0.89
     exchangers
    0.77
     chemok
    0.72
    reactive
    0.65
    posY
    0.56
    Scénario
    0.54
    AnimationsModule
    0.52
     mucosal
    0.52
     scarce
    0.52
    Activations Density 0.007%

    No Known Activations