© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    place names of cities and districts

    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
    SBATCH
    -0.73
    InjectAttribute
    -0.69
     transfieras
    -0.68
    setVerticalGroup
    -0.65
    TagMode
    -0.63
     AssemblyProduct
    -0.63
    ternos
    -0.63
    DebuggerStep
    -0.63
    hasMoreElements
    -0.62
    OrWhiteSpace
    -0.61
    POSITIVE LOGITS
     London
    0.98
    London
    0.94
     Seattle
    0.93
     Chicago
    0.90
     Toronto
    0.89
     Angeles
    0.88
     Paris
    0.88
    Seattle
    0.87
     Mumbai
    0.86
     Tokyo
    0.85
    Activations Density 0.449%

    No Known Activations