© 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. 92112
    Prev
    Next
    INDEX
    Explanations

    effect

    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
     /\.
    -0.54
     informée
    -0.52
     /\.(
    -0.52
    âce
    -0.52
    arschijnlijk
    -0.49
    anskje
    -0.49
    antaranya
    -0.49
    verständ
    -0.48
    Concerning
    -0.47
     Documentary
    -0.47
    POSITIVE LOGITS
     any
    0.62
     interventions
    0.59
     GenerationType
    0.57
     Numerade
    0.56
     NSCoder
    0.54
     intervention
    0.50
    CompilerServices
    0.50
    மான
    0.50
    tagens
    0.50
    Referanser
    0.49
    Activations Density 0.003%

    No Known Activations