© 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. 729
    Prev
    Next
    INDEX
    Explanations

    names of places and 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
    存于互联网档案馆
    -0.60
    MLLoader
    -0.49
     Al
    -0.48
    SequentialGroup
    -0.48
    sApp
    -0.46
    mycompany
    -0.46
     bad
    -0.45
     el
    -0.44
     Ny
    -0.44
     pré
    -0.44
    POSITIVE LOGITS
     Chengdu
    0.89
     Hunan
    0.87
     cinese
    0.85
     Guangdong
    0.85
     CHINA
    0.83
     CHINESE
    0.81
     Chinese
    0.80
    China
    0.80
     Cantonese
    0.79
     China
    0.79
    Activations Density 1.444%

    No Known Activations