© 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. 1-CLT-HP
    7. 11921
    Prev
    Next
    INDEX
    Explanations

    class

    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
    <![
    -0.53
     Starr
    -0.46
    })()
    -0.45
    navigationItem
    -0.45
    シング
    -0.42
    STAR
    -0.42
    GHS
    -0.42
     riten
    -0.42
    class
    -0.41
     SSR
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.71
    expandindo
    0.68
     Exacts
    0.67
    rungsseite
    0.66
     estekak
    0.66
    afficheront
    0.65
    IUrlHelper
    0.62
     nahilalakip
    0.62
    MessageState
    0.62
    IsContent
    0.62
    Activations Density 0.076%

    No Known Activations