© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40150
    Prev
    Next
    INDEX
    Explanations

    color

    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
    color
    -0.61
    colour
    -0.55
     Offisielt
    -0.51
    i
    -0.50
    y
    -0.44
     coppia
    -0.42
    hip
    -0.42
    arsal
    -0.41
    h
    -0.40
     cielos
    -0.40
    POSITIVE LOGITS
    contentLoaded
    0.78
    WithIdentifier
    0.76
     resourceCulture
    0.73
    ValueStyle
    0.73
    HomeAsUpEnabled
    0.73
     saites
    0.73
    ChildScrollView
    0.72
     CreateTagHelper
    0.70
     ostavi
    0.69
    RetentionPolicy
    0.69
    Activations Density 0.124%

    No Known Activations