© 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. 4-CLT-HP
    7. 1958
    Prev
    Next
    INDEX
    Explanations

    biological sequences, gene sequences

    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
     surla
    -0.47
     Surfer
    -0.47
    tora
    -0.44
    Hentet
    -0.44
     ChromeDriver
    -0.44
     palvel
    -0.43
    httpMethod
    -0.43
     debilidad
    -0.42
    !*\
    -0.42
     nė
    -0.42
    POSITIVE LOGITS
    httphttps
    0.69
    ftagPool
    0.63
     himo
    0.63
    chained
    0.57
     erk
    0.56
    pezi
    0.55
    "]}
    0.54
     fired
    0.54
    ByExample
    0.52
    DoubleQuotes
    0.52
    Activations Density 0.005%

    No Known Activations