© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3479
    Prev
    Next
    INDEX
    Explanations

    references to the membrane component involved in manufacturing or biological functions

    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
    iastes
    -0.68
     surface
    -0.61
     Callaway
    -0.61
     surfaces
    -0.59
     kühl
    -0.57
    moiselle
    -0.56
    surface
    -0.55
     поверхности
    -0.55
     OMITBAD
    -0.55
     degré
    -0.54
    POSITIVE LOGITS
     membrane
    3.34
     Membrane
    3.09
    membrane
    2.83
    Membrane
    2.80
     membranes
    2.77
     Membran
    2.55
     membran
    2.20
     membrana
    2.05
    memb
    1.59
     мем
    1.59
    Activations Density 0.014%

    No Known Activations