© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13819
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
    enumi
    -0.52
    leton
    -0.49
    findpost
    -0.49
    iados
    -0.49
     temporales
    -0.48
    м
    -0.47
    ansi
    -0.47
    erequisite
    -0.46
    ništ
    -0.46
     próprias
    -0.45
    POSITIVE LOGITS
     ujednoznacz
    0.64
    NUMX
    0.60
    Portail
    0.59
     OFDb
    0.58
    بوابة
    0.57
    subpackage
    0.56
     growth
    0.55
    ngrx
    0.55
    tonsoft
    0.50
    invokeLater
    0.50
    Activations Density 0.371%

    No Known Activations