© 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. 4780
    Prev
    Next
    INDEX
    Explanations

    states

    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
    They
    -0.63
     They
    -0.60
    Their
    -0.59
    حياتها
    -0.58
     ihrer
    -0.57
    their
    -0.56
     ihrem
    -0.55
    These
    -0.55
    these
    -0.53
     متعلقه
    -0.52
    POSITIVE LOGITS
    onshire
    0.60
    клопе
    0.56
    kungen
    0.55
     įva
    0.51
     Спа
    0.50
    phemy
    0.49
    Obrázky
    0.48
    ACIONAL
    0.48
    HttpException
    0.48
     multin
    0.48
    Activations Density 0.001%

    No Known Activations