© 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. 0-CLT-HP
    7. 41251
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

    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
     themſelves
    -1.11
     Majefty
    -1.05
     Houſe
    -1.02
     itſelf
    -1.01
     Theſe
    -0.99
     himſelf
    -0.98
     ſmall
    -0.96
     Anſ
    -0.94
     définiti
    -0.94
     réguli
    -0.93
    POSITIVE LOGITS
     ag
    0.58
    ist
    0.57
     order
    0.57
     sub
    0.56
     re
    0.55
     (
    0.55
     let
    0.55
     details
    0.54
     impact
    0.53
     over
    0.52
    Activations Density 0.808%

    No Known Activations