© 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. 0-CLT-HP
    7. 93499
    Prev
    Next
    INDEX
    Explanations

    feel

    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
     ſtate
    -0.81
     Anſ
    -0.79
     houſe
    -0.78
     ſtand
    -0.77
     ſta
    -0.77
     Theſe
    -0.76
     ſche
    -0.75
     Reſ
    -0.75
     greateſt
    -0.72
     ſch
    -0.71
    POSITIVE LOGITS
     فريبيس
    0.47
    oneofs
    0.47
     the
    0.45
    GEBURTSDATUM
    0.44
    alai
    0.43
     super
    0.42
     accro
    0.42
    GOTREF
    0.41
     me
    0.41
     ok
    0.40
    Activations Density 0.056%

    No Known Activations