© 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. 1-CLT-HP
    7. 12466
    Prev
    Next
    INDEX
    Explanations

    e

    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
    ]<<
    -0.58
    кипедия
    -0.53
    REFERENCE
    -0.51
     risk
    -0.51
     journal
    -0.50
     Box
    -0.50
    ture
    -0.50
    mce
    -0.49
     office
    -0.49
    tand
    -0.49
    POSITIVE LOGITS
    aarrggbb
    0.68
     sää
    0.59
     internos
    0.50
    OpenHelper
    0.50
    tagext
    0.50
     marinho
    0.49
    省市镇
    0.48
     stället
    0.48
     pluie
    0.48
     sanitarias
    0.48
    Activations Density 0.013%

    No Known Activations