© 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. 92728
    Prev
    Next
    INDEX
    Explanations

    names

    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
     continuant
    -0.49
    esian
    -0.49
     eas
    -0.48
     cleared
    -0.48
    entiated
    -0.47
    ốt
    -0.47
    scription
    -0.47
     AspNetCore
    -0.47
    orable
    -0.47
    bouquet
    -0.46
    POSITIVE LOGITS
    parseFrom
    0.59
     visse
    0.59
     surla
    0.55
     réfugiés
    0.54
    ItemBackground
    0.52
    Климат
    0.52
    basicConfig
    0.52
     fumée
    0.52
    InjectAttribute
    0.51
    ніципалі
    0.51
    Activations Density 0.004%

    No Known Activations