© 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. 91827
    Prev
    Next
    INDEX
    Explanations

    future events/updates

    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
    RegressionTest
    -0.70
    oneofs
    -0.66
    клопе
    -0.65
     otomatig
    -0.64
    <eos>
    -0.63
    errHandler
    -0.63
    FilterChain
    -0.61
     Hiros
    -0.60
     חיצוניים
    -0.60
     foon
    -0.60
    POSITIVE LOGITS
     IConfiguration
    0.47
    ül
    0.47
     Previous
    0.44
     PREVIOUS
    0.43
     earlier
    0.42
     last
    0.42
    last
    0.42
    原神
    0.42
     tham
    0.40
    simo
    0.40
    Activations Density 0.017%

    No Known Activations