© 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. 5-CLT-HP
    7. 92643
    Prev
    Next
    INDEX
    Explanations

    historical/factual content

    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
     CURIAM
    -0.56
    transQ
    -0.54
    PointerException
    -0.54
    cplusplus
    -0.52
    SNAPSHOT
    -0.52
    ISCHE
    -0.51
    Koordin
    -0.49
    Viited
    -0.48
     calciatore
    -0.47
    handa
    -0.47
    POSITIVE LOGITS
     الحره
    0.76
     صوتيه
    0.57
    MemoryWarning
    0.55
    DoubleQuotes
    0.52
     saites
    0.52
    PyExc
    0.51
    keth
    0.50
    énario
    0.48
    Билгалдахарш
    0.48
     المعيارى
    0.48
    Activations Density 0.008%

    No Known Activations