© 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. 20-CLT-HP
    7. 72212
    Prev
    Next
    INDEX
    Explanations

    computing and documentation

    np_max-act-logits · 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
    -0.76
    rungsseite
    -0.70
    ьаж
    -0.60
     AssemblyTitle
    -0.60
     informée
    -0.58
     initComponents
    -0.58
     noDo
    -0.57
    brainly
    -0.56
     Bintang
    -0.54
    GEBURTSDATUM
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.59
     app
    0.50
    iprot
    0.48
    findpost
    0.48
     App
    0.45
    opedic
    0.45
    ionine
    0.45
    app
    0.44
    setShow
    0.44
    уд
    0.44
    Activations Density 0.000%

    No Known Activations