© 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. 10525
    Prev
    Next
    INDEX
    Explanations

    Server/data management

    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
     propOrder
    -0.73
    حوالہ
    -0.71
     незавершена
    -0.70
    Personendaten
    -0.66
     <<<<<<<<<<<<<<
    -0.66
     nahilalakip
    -0.63
     utafitiHapana
    -0.63
    ьаж
    -0.63
     بيها
    -0.59
    featureID
    -0.53
    POSITIVE LOGITS
    DockStyle
    0.79
     Beste
    0.48
     Strateg
    0.45
     Harlequin
    0.44
     Nae
    0.44
    ையில்
    0.44
     Greenland
    0.43
     Simpli
    0.43
    はじめに
    0.43
     Treasures
    0.43
    Activations Density 0.027%

    No Known Activations