© 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. 2-RES-MATRYOSHKA-DC
    7. 4774
    Prev
    Next
    INDEX
    Explanations

    references to specific research projects or funding related to the AR (Androgen Receptor)

    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
    enheim
    -0.68
    CIOS
    -0.68
    Curtis
    -0.62
     Curtis
    -0.62
     Meier
    -0.61
     Ibarra
    -0.60
    لاثة
    -0.60
     Wallflower
    -0.60
     Meg
    -0.59
     metallo
    -0.59
    POSITIVE LOGITS
     AR
    2.61
    AR
    2.17
    ARL
    0.98
     Augmented
    0.92
    ARMA
    0.82
    setupUi
    0.78
     ARP
    0.78
     ARMS
    0.77
    IAR
    0.73
     Nian
    0.72
    Activations Density 0.029%

    No Known Activations