© 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. 3-RES-MATRYOSHKA-DC
    7. 2909
    Prev
    Next
    INDEX
    Explanations

    mentions of lipids and lipid bilayers.

    oai_token-act-pair · gemini-2.0-flash
    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
    AutoField
    -0.73
    queryInterface
    -0.73
     Exacts
    -0.64
    Kilder
    -0.64
    olingo
    -0.63
     FetchType
    -0.62
    CodedInputStream
    -0.62
    lorette
    -0.62
     بيها
    -0.62
     pica
    -0.62
    POSITIVE LOGITS
     lipid
    2.48
     Lipid
    2.20
     lipids
    2.16
    Lipid
    2.06
    lipid
    2.05
    lipids
    1.72
     cholesterol
    1.41
     Lip
    1.35
    olesterol
    1.22
    Lip
    1.19
    Activations Density 0.103%

    No Known Activations