© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    Mixed data

    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
    pada
    -0.57
    ManagedBean
    -0.56
    RetentionPolicy
    -0.55
    iecie
    -0.54
     كورة
    -0.54
    autogui
    -0.52
    hamcrest
    -0.52
     average
    -0.51
     alone
    -0.50
    lalu
    -0.49
    POSITIVE LOGITS
     Waray
    0.71
    RUnlock
    0.58
    tagHelperRunner
    0.54
     defaultstate
    0.54
    onedDateTime
    0.52
     EconPapers
    0.52
     educativos
    0.52
     masculinos
    0.52
    RectangleBorder
    0.51
    (")");
    0.51
    Activations Density 0.244%

    No Known Activations