© 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. 1-CLT-HP
    7. 10329
    Prev
    Next
    INDEX
    Explanations

    import

    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
    WithIOException
    -0.79
    elemField
    -0.76
     utafitiHapana
    -0.71
     متعلقه
    -0.71
     kaarangay
    -0.71
     <=",
    -0.65
    EDEFAULT
    -0.65
     nahilalakip
    -0.62
    homonymie
    -0.62
    AsUp
    -0.61
    POSITIVE LOGITS
    Synonymes
    0.55
    VersionUID
    0.55
    ArgsConstructor
    0.54
     pleaſure
    0.52
     Enrique
    0.50
    Espèce
    0.48
     Diſ
    0.47
     ſtate
    0.47
     Willard
    0.46
     Erick
    0.46
    Activations Density 4.358%

    No Known Activations