© 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. 1-CLT-HP
    7. 14681
    Prev
    Next
    INDEX
    Explanations

    medical

    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
    ValueStyle
    -0.77
    ſelf
    -0.77
    Билгалдахарш
    -0.77
    rungsseite
    -0.77
     EconPapers
    -0.76
    ſelves
    -0.75
     snippetHide
    -0.73
     purpoſe
    -0.71
    ChildScrollView
    -0.70
     $_"
    -0.69
    POSITIVE LOGITS
     uș
    0.45
     aphids
    0.40
    nodeValue
    0.39
    shutil
    0.38
    elski
    0.38
     Refin
    0.38
    収
    0.37
    dorf
    0.36
     <
    0.36
     anyone
    0.35
    Activations Density 0.026%

    No Known Activations