© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    the letters "ea" followed by a non-space character

    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
    Hochspringen
    -0.77
    ibouti
    -0.73
     nahilalakip
    -0.71
    Mayer
    -0.70
     Giuliani
    -0.69
    Fiche
    -0.68
     Rudolph
    -0.67
     trajets
    -0.66
    fillType
    -0.66
    ‍♀️
    -0.66
    POSITIVE LOGITS
    ea
    1.66
     Lea
    1.30
    Lea
    1.26
    eam
    1.20
    EA
    1.20
     ea
    1.18
     ear
    1.17
    EAR
    1.16
    rea
    1.14
     Rea
    1.13
    Activations Density 0.314%

    No Known Activations