© 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. 2848
    Prev
    Next
    INDEX
    Explanations

    in

    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
     χρήση
    -0.53
     in
    -0.47
    DoubleQuotes
    -0.47
    Források
    -0.44
    deaux
    -0.44
     using
    -0.42
    gelen
    -0.42
    verifyException
    -0.41
     with
    -0.41
    Erreferentziak
    -0.40
    POSITIVE LOGITS
     GetEnumerator
    0.64
     мәкал
    0.60
    modb
    0.59
    شهاد
    0.57
    ArrowToggle
    0.57
    JspWriter
    0.56
     speelt
    0.56
     tolerated
    0.54
     noqa
    0.54
    ंदीखरीदारी
    0.54
    Activations Density 0.002%

    No Known Activations