© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38595
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
     orange
    -0.74
     Forest
    -0.74
     Orange
    -0.69
    Orange
    -0.65
     ORANGE
    -0.57
     FOREST
    -0.56
    terraform
    -0.56
    orange
    -0.53
    Forest
    -0.52
    ORANGE
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.89
    enumi
    0.64
     Theſe
    0.62
     comuniques
    0.62
    hdys
    0.61
     ſche
    0.61
    xase
    0.60
     Houſe
    0.60
     HttpNotFound
    0.58
     الحره
    0.58
    Activations Density 1.068%

    No Known Activations