© 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. 6302
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hu" or references related to "Hu" in the text

    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
     fubject
    -0.81
     againſt
    -0.79
    stateProvider
    -0.74
    EndInit
    -0.73
     itſelf
    -0.73
     fufficient
    -0.72
     uſ
    -0.69
     Pyrr
    -0.69
     pleaſure
    -0.69
     firſt
    -0.69
    POSITIVE LOGITS
    hu
    3.02
     hu
    2.86
     Hu
    2.83
    Hu
    2.81
    HU
    2.67
     HU
    2.44
    ahu
    1.29
     Huff
    1.13
    Huff
    1.09
    hum
    1.06
    Activations Density 0.027%

    No Known Activations