© 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. 20-CLT-HP
    7. 76515
    Prev
    Next
    INDEX
    Explanations

    Biology/medical context

    np_max-act-logits · 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
     lenker
    -0.92
     disambiguazione
    -0.87
    
    -0.81
     <",
    -0.68
    rungsseite
    -0.67
    Personendaten
    -0.67
     CreateTagHelper
    -0.66
    writeFieldEnd
    -0.64
    homonymie
    -0.63
    InstrumentedTest
    -0.63
    POSITIVE LOGITS
     extra
    0.59
     random
    0.59
    extra
    0.58
     trans
    0.57
    random
    0.57
    basicConfig
    0.56
     chemo
    0.56
     dia
    0.55
     Che
    0.54
    Che
    0.54
    Activations Density 0.003%

    No Known Activations