© 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. 4-CLT-HP
    7. 44
    Prev
    Next
    INDEX
    Explanations

    ground

    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
     ostavi
    -0.59
    FXMLLoader
    -0.55
    readyState
    -0.53
    abetes
    -0.50
     accom
    -0.48
    beat
    -0.48
    elett
    -0.47
     Ac
    -0.47
    makeText
    -0.46
    plants
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.56
    الإنجليزية
    0.53
     متعلقه
    0.49
    enumi
    0.48
     genoeg
    0.47
     quelcon
    0.47
    }};
    0.46
     variés
    0.46
     ویکی‌پدیا
    0.46
     PhpStorm
    0.45
    Activations Density 0.005%

    No Known Activations