© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    medical imaging and scans

    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
    parsedMessage
    -0.93
    tvguidetime
    -0.66
    DockStyle
    -0.65
    Попис
    -0.63
    Clik
    -0.62
     parseFrom
    -0.61
     kasarigan
    -0.60
    Rüyada
    -0.59
    Revenir
    -0.56
     scrimmage
    -0.56
    POSITIVE LOGITS
    serviceWorker
    0.50
    setLayoutParams
    0.49
    tonode
    0.47
     machine
    0.47
    andExpect
    0.47
    ologist
    0.46
    ginfo
    0.44
    kheim
    0.44
     room
    0.44
     متحده
    0.44
    Activations Density 0.001%

    No Known Activations