© 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. 0-CLT-HP
    7. 94801
    Prev
    Next
    INDEX
    Explanations

    improvements

    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
     improvement
    -1.76
    improvement
    -1.64
    improve
    -1.52
     improvements
    -1.49
     Improvement
    -1.46
    Improvement
    -1.45
     IMPROVEMENT
    -1.40
     improve
    -1.38
    Improve
    -1.34
     IMPROV
    -1.33
    POSITIVE LOGITS
     later
    0.52
     doubt
    0.48
     doubts
    0.43
    đồng
    0.43
     odds
    0.41
     made
    0.41
     you
    0.41
    意思
    0.41
     guess
    0.41
     guessing
    0.40
    Activations Density 0.054%

    No Known Activations