© 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. 15372
    Prev
    Next
    INDEX
    Explanations

    era

    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
    era
    -0.89
    WebVitals
    -0.68
    ERA
    -0.59
    TargetException
    -0.52
    kül
    -0.48
    sa
    -0.46
    shi
    -0.46
    yl
    -0.45
    ayan
    -0.44
    san
    -0.44
    POSITIVE LOGITS
     ostavi
    0.65
    RRect
    0.64
    styleType
    0.62
    complexContent
    0.61
    GEBURTSDATUM
    0.60
    Cordialement
    0.59
    extAlignment
    0.59
    rijfs
    0.58
    تفصیلات
    0.55
    ChildScrollView
    0.54
    Activations Density 0.035%

    No Known Activations