© 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. 0-CLT-HP
    7. 94205
    Prev
    Next
    INDEX
    Explanations

    Cellular

    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
    roek
    -0.65
     MessageBoxIcon
    -0.65
     समीक्षाओं
    -0.62
    出版年
    -0.61
     syndic
    -0.61
    λίου
    -0.61
    VOL
    -0.60
     pinulongan
    -0.60
    ADIAN
    -0.60
    esModule
    -0.59
    POSITIVE LOGITS
    はじめに
    0.53
     propOrder
    0.48
     незавершена
    0.44
    Personendaten
    0.43
     mergeFrom
    0.42
     secretos
    0.41
    i
    0.41
    клопе
    0.40
    站
    0.40
     Rueda
    0.40
    Activations Density 1.456%

    No Known Activations