© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73658
    Prev
    Next
    INDEX
    Explanations

    Diverse topics

    np_max-act-logits · 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
     sections
    -0.97
     section
    -0.93
     secciones
    -0.92
     Sections
    -0.90
    Sections
    -0.90
    sections
    -0.89
     SECTIONS
    -0.86
     Section
    -0.80
     SECTION
    -0.78
    section
    -0.76
    POSITIVE LOGITS
     wonderful
    0.63
     lasting
    0.63
     sweet
    0.59
     fond
    0.57
    mapreduce
    0.55
     }}"></
    0.52
     amazing
    0.52
     happy
    0.50
     warm
    0.50
    webElement
    0.49
    Activations Density 0.000%

    No Known Activations