© 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. 2002
    Prev
    Next
    INDEX
    Explanations

    the word "surface"

    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
    GenerationType
    -0.90
     متعلقه
    -0.89
    aarrggbb
    -0.82
    FieldBuilder
    -0.81
    новниш
    -0.78
     Pietro
    -0.77
    MLLoader
    -0.76
    MethodManager
    -0.74
    enumii
    -0.73
     SEDS
    -0.72
    POSITIVE LOGITS
     surface
    3.33
     Surface
    3.03
    surface
    3.00
    Surface
    2.92
     surfaces
    2.80
     SURFACE
    2.80
    SURFACE
    2.53
     Surfaces
    2.52
    surfaces
    2.48
    urface
    2.28
    Activations Density 0.099%

    No Known Activations