© 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. 5-CLT-HP
    7. 899
    Prev
    Next
    INDEX
    Explanations

    the

    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
     snart
    -0.63
     bientôt
    -0.63
     Soon
    -0.57
    Soon
    -0.57
     faſt
    -0.56
     ujednoznacz
    -0.54
     prochain
    -0.54
     feeding
    -0.51
     soon
    -0.51
     rapidly
    -0.50
    POSITIVE LOGITS
    Filmografia
    0.67
    hésite
    0.59
     previous
    0.59
     currently
    0.58
     previously
    0.58
     sejauh
    0.57
     semasa
    0.57
     prior
    0.56
     vorige
    0.56
     earlier
    0.55
    Activations Density 0.011%

    No Known Activations