© 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. 5-CLT-HP
    7. 94937
    Prev
    Next
    INDEX
    Explanations

    current

    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
     שוליים
    -0.75
    IBOutlet
    -0.74
    middels
    -0.72
    UnitTesting
    -0.70
    WebVitals
    -0.69
    GEBURTSDATUM
    -0.68
     }}"></
    -0.68
     myſelf
    -0.63
     Theſe
    -0.63
     IBOutlet
    -0.62
    POSITIVE LOGITS
     so
    0.51
    tilhar
    0.48
    sizeCache
    0.47
     qu
    0.45
    ERA
    0.45
    ovács
    0.44
    $_['
    0.44
     push
    0.43
    getDriver
    0.43
    toMatch
    0.43
    Activations Density 0.002%

    No Known Activations