© 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. 4-CLT-HP
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    rating

    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
     resourceCulture
    -0.62
    AndroidJUnit
    -0.56
    visející
    -0.53
    enumii
    -0.53
    Према
    -0.52
    LogFactory
    -0.52
     rayures
    -0.51
    TintMode
    -0.50
    postIndex
    -0.50
    acaktır
    -0.49
    POSITIVE LOGITS
    //
    0.52
    <bos>
    0.50
    หมือน
    0.47
    phosa
    0.46
     oprot
    0.46
    Spel
    0.46
     surfboard
    0.46
    DMETHOD
    0.45
    osoba
    0.45
    RegisterType
    0.45
    Activations Density 0.009%

    No Known Activations