© 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. 1-CLT-HP
    7. 14999
    Prev
    Next
    INDEX
    Explanations

    read

    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
     reading
    -1.17
    reading
    -1.03
     read
    -1.01
     reads
    -0.91
     READING
    -0.88
    Reading
    -0.88
     Reading
    -0.88
    อ่าน
    -0.86
    read
    -0.81
     Reads
    -0.80
    POSITIVE LOGITS
     defaultstate
    0.65
    rechnung
    0.48
    انس
    0.47
    ApiRequest
    0.45
     Schaff
    0.45
    церт
    0.45
    reqs
    0.45
     Svg
    0.43
    ย์
    0.43
    étique
    0.43
    Activations Density 0.008%

    No Known Activations