© 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. 10068
    Prev
    Next
    INDEX
    Explanations

    uge

    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
     viewDidLoad
    -0.84
    twimg
    -0.75
    참고
    -0.74
    DockStyle
    -0.72
    httphttps
    -0.71
     referrerpolicy
    -0.71
     insuffisamment
    -0.68
    parsedMessage
    -0.67
    LookAnd
    -0.65
    Hozzáférés
    -0.65
    POSITIVE LOGITS
     brancas
    0.52
    ropractic
    0.43
     âmes
    0.43
     blancas
    0.42
    Ac
    0.41
     vocales
    0.40
     jár
    0.40
     tangan
    0.39
    If
    0.39
     vocale
    0.38
    Activations Density 0.019%

    No Known Activations