© 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. 3-RES-MATRYOSHKA-DC
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    variants of "hem", especially within scientific contexts.

    oai_token-act-pair · gemini-2.0-flash
    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
    :✨
    -0.75
    Билгалдахарш
    -0.72
    #
    -0.67
     estekak
    -0.66
    setVerticalGroup
    -0.66
    routeProvider
    -0.65
     Audiodateien
    -0.63
     Mancha
    -0.61
     defaultstate
    -0.61
    INGO
    -0.60
    POSITIVE LOGITS
    ae
    1.34
    AE
    1.06
     ae
    0.99
     Ae
    0.85
     AE
    0.85
    tae
    0.84
    bae
    0.79
     nae
    0.79
     Hae
    0.78
    aer
    0.75
    Activations Density 0.259%

    No Known Activations