© 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. 0-RES-MATRYOSHKA-DC
    7. 12810
    Prev
    Next
    INDEX
    Explanations

    references to aerial lifts and mentions of the city Moscow

    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
     nahilalakip
    -0.71
    XmlAccessType
    -0.59
    principalColumn
    -0.57
     Celle
    -0.56
    iprot
    -0.55
     inspect
    -0.53
     Seoul
    -0.52
     sappi
    -0.52
     Nordrhein
    -0.52
    IMPORTED
    -0.52
    POSITIVE LOGITS
     aerial
    0.89
     Moscow
    0.88
    Sm
    0.83
     Sm
    0.82
    Aerial
    0.77
     Aerial
    0.76
    aerial
    0.75
    aarrggbb
    0.71
    Moscow
    0.70
     AssemblyTitle
    0.66
    Activations Density 0.012%

    No Known Activations