© 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. 77629
    Prev
    Next
    INDEX
    Explanations

    computing, medicine, names

    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
    انيف
    -0.67
     nahilalakip
    -0.63
    OGND
    -0.57
    ftant
    -0.57
    plans
    -0.55
     scolaires
    -0.54
     disambiguazione
    -0.53
     romantis
    -0.51
     män
    -0.51
     rispet
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.66
    UserScript
    0.60
     sumpay
    0.59
    gridx
    0.53
     team
    0.52
    sizeCache
    0.51
    ViewImports
    0.50
    __":
    0.49
    limus
    0.47
     Team
    0.45
    Activations Density 0.012%

    No Known Activations