© 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. 5-CLT-HP
    7. 93014
    Prev
    Next
    INDEX
    Explanations

    development

    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
     of
    -0.71
     Open
    -0.51
     defStyleAttr
    -0.48
     CHtml
    -0.47
     Conc
    -0.47
    instancetype
    -0.44
     Box
    -0.44
     Molo
    -0.43
     open
    -0.42
     Laser
    -0.42
    POSITIVE LOGITS
     by
    0.78
     للاسماء
    0.73
    UnusedPrivate
    0.73
    참고
    0.65
     дописавши
    0.62
     oleh
    0.59
     propOrder
    0.58
    by
    0.57
    Попис
    0.56
     kaarangay
    0.56
    Activations Density 0.003%

    No Known Activations