© 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. 5-CLT-HP
    7. 91408
    Prev
    Next
    INDEX
    Explanations

    medical imaging/therapies

    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
    RequestParam
    -0.62
     disponibilités
    -0.61
    +#+
    -0.59
     CreateTagHelper
    -0.58
    makeConstraints
    -0.57
     спро
    -0.53
     AppBundle
    -0.52
    簧
    -0.52
    ikou
    -0.52
    EDEFAULT
    -0.51
    POSITIVE LOGITS
    ValueGeneration
    0.54
     Agent
    0.52
     &___
    0.50
    poons
    0.49
    agents
    0.49
     AGENT
    0.49
    Agent
    0.47
     WaitForSeconds
    0.47
     agent
    0.47
    voyez
    0.47
    Activations Density 0.008%

    No Known Activations