© 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. 4857
    Prev
    Next
    INDEX
    Explanations

    and

    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
     dignité
    -0.63
     seules
    -0.52
     löyty
    -0.51
     seuls
    -0.51
     löytyy
    -0.50
    paravant
    -0.50
     Their
    -0.49
     fondament
    -0.48
     stället
    -0.46
     démocr
    -0.46
    POSITIVE LOGITS
     its
    0.95
     the
    0.94
     his
    0.90
     researcher
    0.78
     others
    0.78
    findpost
    0.76
     politician
    0.76
     educator
    0.75
     configureStore
    0.73
     farmer
    0.73
    Activations Density 0.009%

    No Known Activations