© 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. 12752
    Prev
    Next
    INDEX
    Explanations

    references to specific robotic characters and their distinctive equipment or attributes

    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
     organism
    -0.71
     Francisco
    -0.64
     organisms
    -0.57
    Бахар
    -0.54
    quadro
    -0.52
    äumt
    -0.52
    imarães
    -0.51
    ワー
    -0.50
    //}
    -0.50
    swagger
    -0.50
    POSITIVE LOGITS
     Gar
    2.20
    Gar
    2.14
     gar
    1.06
     GAR
    0.94
     Гар
    0.71
    UrlResolution
    0.69
    Гар
    0.66
     مرئيه
    0.62
     Garland
    0.60
     Garde
    0.60
    Activations Density 0.001%

    No Known Activations