© 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. 1-RES-MATRYOSHKA-DC
    7. 939
    Prev
    Next
    INDEX
    Explanations

    references to the surface or surface-related features of materials

    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
     متعلقه
    -0.77
    aarrggbb
    -0.71
     materiales
    -0.69
     materials
    -0.66
     materie
    -0.66
     MATERIALS
    -0.64
     MATERIAL
    -0.62
    WriteBarrier
    -0.62
    conteudo
    -0.61
     Materialien
    -0.60
    POSITIVE LOGITS
     surface
    4.81
     Surface
    4.34
    surface
    4.28
    Surface
    4.13
     SURFACE
    3.94
     surfaces
    3.55
    SURFACE
    3.48
     Surfaces
    3.20
    urface
    3.05
    surfaces
    3.05
    Activations Density 0.035%

    No Known Activations