© 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. 0-CLT-HP
    7. 92808
    Prev
    Next
    INDEX
    Explanations

    code

    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
     оригіналу
    -0.76
     apprendre
    -0.70
     Pingback
    -0.59
    !*\
    -0.59
    AutoScale
    -0.59
    hdys
    -0.59
     démocr
    -0.59
     velours
    -0.56
    SaveChangesAsync
    -0.56
     engagé
    -0.56
    POSITIVE LOGITS
    ########.
    0.57
    prüche
    0.56
    (")");
    0.55
    ifikationer
    0.52
    ăzi
    0.50
     conftest
    0.49
    rungsseite
    0.48
    iettivo
    0.48
     handleMessage
    0.48
    💼
    0.47
    Activations Density 1.597%

    No Known Activations