© 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. 0-CLT-HP
    7. 92551
    Prev
    Next
    INDEX
    Explanations

    biology, medicine

    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
     Transplant
    -0.59
     gynhyrchwyd
    -0.57
     noastre
    -0.56
     définiti
    -0.56
     AppComponent
    -0.55
    IUrlHelper
    -0.54
    DeleteBehavior
    -0.53
     Ause
    -0.52
    RuleContext
    -0.51
    skjaer
    -0.50
    POSITIVE LOGITS
    ing
    1.16
    ation
    0.73
    ING
    0.71
    ning
    0.64
    ous
    0.63
    ed
    0.59
    sto
    0.59
    let
    0.57
    ה
    0.57
    ial
    0.55
    Activations Density 2.030%

    No Known Activations