© 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. 1-RES-MATRYOSHKA-DC
    7. 1173
    Prev
    Next
    INDEX
    Explanations

    references to the performance metric "area under the ROC curve" (AUC)

    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
     Marshall
    -0.69
    HandleFunc
    -0.68
     Poul
    -0.67
    Marshall
    -0.65
     Fontaine
    -0.65
    idt
    -0.62
     Conroy
    -0.62
    marshall
    -0.62
    jstor
    -0.60
    ErrUnexpectedEOF
    -0.60
    POSITIVE LOGITS
     PE
    1.99
    Pe
    1.92
     pe
    1.91
     Pe
    1.90
    PE
    1.88
    pe
    1.85
     PEAK
    1.63
     Peta
    1.60
    PET
    1.59
    petition
    1.55
    Activations Density 1.099%

    No Known Activations