© 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. 15234
    Prev
    Next
    INDEX
    Explanations

    learning and code

    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
     Learning
    -1.09
     learning
    -1.09
    tagHelperRunner
    -1.06
     learner
    -1.05
     LEARNING
    -0.99
    Learning
    -0.98
    learning
    -0.98
     learners
    -0.96
     Learners
    -0.94
     Learner
    -0.93
    POSITIVE LOGITS
     Efq
    0.46
     Majefty
    0.46
     ſhe
    0.44
     stylo
    0.42
     Monfieur
    0.41
     ſhall
    0.41
    npr
    0.41
     fhew
    0.41
     çekilen
    0.40
     штат
    0.40
    Activations Density 0.003%

    No Known Activations