© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    phrases that express a percentage or commonality of people

    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
     CreateTagHelper
    -0.60
    Constantes
    -0.57
    дца
    -0.57
    fara
    -0.56
    נה
    -0.54
    #
    -0.53
    leyeb
    -0.53
    異なる
    -0.52
    arsal
    -0.52
    รม
    -0.51
    POSITIVE LOGITS
     flesta
    1.30
     majority
    1.20
     plupart
    1.18
     большинство
    1.18
    大部分
    1.15
     fleste
    1.14
     meisten
    1.13
     maioria
    1.13
    Majority
    1.10
    majority
    1.09
    Activations Density 0.712%

    No Known Activations