© 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. 1-CLT-HP
    7. 13157
    Prev
    Next
    INDEX
    Explanations

    medicine and biology

    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
     glaucoma
    -0.59
     временем
    -0.48
    Бахар
    -0.47
    venty
    -0.46
     GST
    -0.46
    исленность
    -0.46
    ventud
    -0.44
    ünstig
    -0.42
    bigliamento
    -0.42
     car
    -0.40
    POSITIVE LOGITS
     wireType
    0.69
    ="@+
    0.68
    ContentAlignment
    0.66
    expandindo
    0.64
    writeFieldEnd
    0.63
    Datuak
    0.61
    .$_
    0.59
    ///</
    0.59
     gawas
    0.57
    valentino
    0.57
    Activations Density 0.054%

    No Known Activations