© 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. 5-CLT-HP
    7. 93040
    Prev
    Next
    INDEX
    Explanations

    medicine/biology/chemistry

    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
     đôi
    -0.49
    orneys
    -0.44
     ome
    -0.44
    efeller
    -0.44
     disulfide
    -0.44
     hoodie
    -0.44
    ite
    -0.44
    unat
    -0.43
     distanciation
    -0.43
    otry
    -0.43
    POSITIVE LOGITS
    EndContext
    0.68
    expandindo
    0.65
    tagHelperRunner
    0.63
     CreateTagHelper
    0.62
    ClientRect
    0.61
    RegressionTest
    0.59
    UnsafeEnabled
    0.59
    localctx
    0.58
    princ
    0.56
    clyde
    0.56
    Activations Density 0.002%

    No Known Activations