© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13400
    Prev
    Next
    INDEX
    Explanations

    references or mentions of Manchester

    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
    ffindor
    -0.62
     disambiguazione
    -0.54
     propOrder
    -0.53
     Drou
    -0.50
    buzo
    -0.50
     Phipps
    -0.49
    
    -0.49
     quæ
    -0.48
    createForm
    -0.48
     creo
    -0.48
    POSITIVE LOGITS
     Kum
    2.11
    Kum
    2.05
    kum
    1.59
     kum
    1.52
     Kumar
    1.39
    Kumar
    1.30
    kumar
    1.30
     Lyon
    1.13
     kumar
    1.13
     KUMAR
    1.13
    Activations Density 0.005%

    No Known Activations