© 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. 76536
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    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
     préférences
    -0.48
     supérieurs
    -0.47
    paksa
    -0.47
     extérieurs
    -0.44
    lüssel
    -0.42
     supérieures
    -0.41
    IsContent
    -0.41
     nationaux
    -0.41
    NUS
    -0.41
     industriels
    -0.40
    POSITIVE LOGITS
    __*/
    0.73
    
    0.71
    ImageContext
    0.69
    ScopeManager
    0.63
    Witam
    0.61
     ProtoMessage
    0.61
    <>());
    0.61
    MigrationBuilder
    0.60
    :✨
    0.60
     kaarangay
    0.59
    Activations Density 0.001%

    No Known Activations