© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42760
    Prev
    Next
    INDEX
    Explanations

    completeness or high degree

    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
    WebVitals
    -0.70
    GEBURTSDATUM
    -0.61
     kasarigan
    -0.59
    ksikon
    -0.57
     Wikimedijinoj
    -0.56
     pouvoit
    -0.55
    acana
    -0.52
    weeks
    -0.51
     auroit
    -0.51
     vectorielles
    -0.49
    POSITIVE LOGITS
    QMetaType
    0.56
    !
    0.56
    出版年
    0.55
    сылкі
    0.54
    WebControls
    0.54
    RenderAtEndOf
    0.54
     ско
    0.50
    ↵↵
    0.48
    IntentFilter
    0.46
    PYX
    0.46
    Activations Density 0.133%

    No Known Activations