© 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. 5503
    Prev
    Next
    INDEX
    Explanations

    mentions of water leakage or fluid leaks

    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
    groom
    -0.57
     agonists
    -0.56
    LUT
    -0.55
    bahn
    -0.54
     DeWitt
    -0.53
     scrollView
    -0.52
     agonist
    -0.51
    AfterViewInit
    -0.51
     свер
    -0.51
    swal
    -0.50
    POSITIVE LOGITS
     leak
    3.31
     leakage
    3.28
     leaks
    3.09
    leak
    3.09
     Leakage
    2.98
     Leak
    2.92
    Leak
    2.91
     leaking
    2.80
     leaked
    2.69
     Leaks
    2.58
    Activations Density 0.009%

    No Known Activations