© 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. 3-RES-MATRYOSHKA-DC
    7. 1403
    Prev
    Next
    INDEX
    Explanations

    the word "top."

    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
     AssemblyCulture
    -0.84
    новниш
    -0.69
    TagMode
    -0.67
    ölkerung
    -0.65
    UnsafeEnabled
    -0.64
    AddTagHelper
    -0.63
    iestety
    -0.60
     biber
    -0.60
     MonoBehaviour
    -0.58
    ValueStyle
    -0.58
    POSITIVE LOGITS
     top
    3.53
    top
    3.19
     Top
    3.16
    Top
    3.08
     TOP
    3.02
    TOP
    2.86
     tops
    2.70
    tops
    2.38
     Tops
    2.22
    getTop
    2.20
    Activations Density 0.220%

    No Known Activations