© 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. 2-RES-MATRYOSHKA-DC
    7. 5100
    Prev
    Next
    INDEX
    Explanations

    references to physical surfaces or surfaces where interactions occur

    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
     LAYER
    -0.98
     wall
    -0.96
     Membrane
    -0.96
     Layer
    -0.96
     membrane
    -0.94
     walls
    -0.93
     Walls
    -0.92
     layer
    -0.92
     membranes
    -0.92
     SKIN
    -0.90
    POSITIVE LOGITS
     surface
    1.98
     Surface
    1.85
    surface
    1.81
    Surface
    1.79
     SURFACE
    1.65
    SURFACE
    1.44
     surfaces
    1.32
     superfície
    1.20
    surfaces
    1.18
     superficie
    1.17
    Activations Density 0.035%

    No Known Activations