© 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. 1720
    Prev
    Next
    INDEX
    Explanations

    the letter "ç" or "Ç"

    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
    ArgumentParser
    -0.79
    GEBURTSDATUM
    -0.75
    міністра
    -0.75
    å
    -0.75
    ScopeManager
    -0.70
     Neb
    -0.69
    styleType
    -0.69
    terscotch
    -0.69
    getColumnIndex
    -0.69
     rospy
    -0.68
    POSITIVE LOGITS
    ç
    2.69
    Ç
    1.61
     ç
    1.20
    çi
    1.05
    ccedil
    1.04
    çu
    1.03
    çe
    1.01
     Ç
    0.98
    ça
    0.92
    çs
    0.89
    Activations Density 0.001%

    No Known Activations