© 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. 91487
    Prev
    Next
    INDEX
    Explanations

    Primates and science

    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
    cdi
    -0.40
    spread
    -0.35
    Confirmation
    -0.35
    oude
    -0.34
     nematodes
    -0.34
     australis
    -0.33
     nematode
    -0.33
     plati
    -0.32
     sting
    -0.32
    PI
    -0.32
    POSITIVE LOGITS
    Демографія
    0.94
    tvguidetime
    0.91
    yntaxException
    0.87
    tanleria
    0.86
    Билгалдахарш
    0.86
    ViewFeatures
    0.85
    Chham
    0.79
    windowFixed
    0.77
    expandindo
    0.77
     AssemblyCulture
    0.76
    Activations Density 0.001%

    No Known Activations