© 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. 2-RES-MATRYOSHKA-DC
    7. 5309
    Prev
    Next
    INDEX
    Explanations

    specific patterns of 'xe' symbols and related measurement parameters

    oai_token-act-pair · gpt-4.1-nano
    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
     pinulongan
    -0.87
    InjectAttribute
    -0.87
    ValueStyle
    -0.85
    tagHelperRunner
    -0.83
     saites
    -0.82
     &___
    -0.81
     الحره
    -0.77
    DNEY
    -0.77
    клопе
    -0.76
     tartalomajánló
    -0.76
    POSITIVE LOGITS
    xe
    3.03
     xe
    1.72
    XE
    1.44
    Xe
    1.36
     Xe
    1.20
     XE
    1.18
    xE
    0.99
    Ve
    0.66
     Ve
    0.63
    je
    0.61
    Activations Density 0.011%

    No Known Activations