© 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. 0-CLT-HP
    7. 1947
    Prev
    Next
    INDEX
    Explanations

    key

    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
     key
    -0.98
     important
    -0.92
     crucial
    -0.79
    important
    -0.73
     major
    -0.71
     belangrijke
    -0.70
    key
    -0.69
    Key
    -0.69
    重要な
    -0.68
     the
    -0.67
    POSITIVE LOGITS
     unknownFields
    1.02
    ThroughAttribute
    1.00
     فريبيس
    0.90
    دانشنامهٔ
    0.89
     }</
    0.87
     photolibrary
    0.85
     doubtnut
    0.85
     Efq
    0.85
     }}$}
    0.84
     Shakspeare
    0.84
    Activations Density 0.242%

    No Known Activations