© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2966
    Prev
    Next
    INDEX
    Explanations

    Beginning of documents

    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
     Monfieur
    -0.86
     myſelf
    -0.83
     raiſ
    -0.80
     Majefty
    -0.80
     Diſ
    -0.79
     Jefus
    -0.79
     uſed
    -0.79
     ſte
    -0.78
     themſelves
    -0.78
     himſelf
    -0.78
    POSITIVE LOGITS
    Personensuche
    0.79
    RenderAtEndOf
    0.73
     kasarigan
    0.68
    OGND
    0.62
     الحره
    0.62
    Datuak
    0.59
     Roskov
    0.59
     lenker
    0.58
    featureID
    0.58
     المعيارى
    0.57
    Activations Density 0.001%

    No Known Activations