© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41834
    Prev
    Next
    INDEX
    Explanations

    hor

    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
    MessageTagHelper
    -0.79
     coasts
    -0.76
    contentLoaded
    -0.71
     loaded
    -0.69
     ExecuteAsync
    -0.65
     ashore
    -0.63
     CanadaChoose
    -0.62
    RenderAtEndOf
    -0.61
     /\.(
    -0.60
     Portail
    -0.59
    POSITIVE LOGITS
    LookAnd
    0.57
     >=",
    0.55
    cinogenicity
    0.54
     opérateur
    0.50
     design
    0.50
    primaryKey
    0.50
     Bezeichnung
    0.49
    ibility
    0.49
    komst
    0.49
    bership
    0.48
    Activations Density 0.287%

    No Known Activations