© 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. 2-RES-MATRYOSHKA-DC
    7. 3779
    Prev
    Next
    INDEX
    Explanations

    references to biological samples, particularly urine, feces, and fecal or urinary excretion data

    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
     Linde
    -0.56
    Története
    -0.56
    palm
    -0.56
     nakalista
    -0.54
    orda
    -0.53
    Mav
    -0.53
     صوتيه
    -0.53
     Coup
    -0.51
     Mav
    -0.51
    нак
    -0.51
    POSITIVE LOGITS
     urine
    2.86
     Urine
    2.63
     urinary
    2.48
    Urine
    2.42
     Urinary
    2.20
     urin
    1.97
     urination
    1.91
     orina
    1.80
     Urin
    1.77
    urine
    1.73
    Activations Density 0.143%

    No Known Activations