© 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. 4-CLT-HP
    7. 4985
    Prev
    Next
    INDEX
    Explanations

    Fortune, time context

    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
    )');
    -0.56
    GraphicsUnit
    -0.55
    GEBURTSDATUM
    -0.54
    XmlEnum
    -0.54
    saco
    -0.54
     IActionResult
    -0.52
     surla
    -0.51
    ]');
    -0.51
     Pero
    -0.50
    setVerticalGroup
    -0.50
    POSITIVE LOGITS
     '\\;'
    0.56
    tagHelperRunner
    0.55
    adaptiveStyles
    0.50
     us
    0.49
    leby
    0.49
    NOPQRST
    0.46
     chúng
    0.46
    legi
    0.44
    кисло
    0.44
     tarta
    0.43
    Activations Density 0.011%

    No Known Activations