© 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. 6-RES-MATRYOSHKA-DC
    7. 169
    Prev
    Next
    INDEX
    Explanations

    words related to surfaces or layers of materials

    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
     Schub
    -0.80
     sauvages
    -0.72
     russes
    -0.71
    CodedInputStream
    -0.70
     chimique
    -0.70
    сылкі
    -0.69
    oiseau
    -0.67
     picioare
    -0.65
     hydrauli
    -0.63
     Minaj
    -0.62
    POSITIVE LOGITS
     surface
    1.52
     surfaces
    1.48
     Surface
    1.38
    surface
    1.32
     Surfaces
    1.29
    Surface
    1.28
    surfaces
    1.26
    urface
    1.20
     SURFACE
    1.20
    SURFACE
    1.13
    Activations Density 1.905%

    No Known Activations