© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 745
    Prev
    Next
    INDEX
    Explanations

    diarrhea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diarrhoea
    -0.79
     diarr
    -0.78
     diarrhea
    -0.63
    GEBURTS
    -0.58
     שוליים
    -0.56
    </thead>
    -0.54
    VIAF
    -0.52
     '\\;'
    -0.50
    KommentareTeilen
    -0.50
     <",
    -0.49
    POSITIVE LOGITS
    ho
    0.56
    he
    0.54
     hydrochloride
    0.52
     nhàng
    0.52
    hes
    0.52
    hoe
    0.51
    дзе
    0.50
    NamedQuery
    0.50
    requireNonNull
    0.50
    CodedInputStream
    0.49
    Activations Density 0.041%

    No Known Activations