© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93055
    Prev
    Next
    INDEX
    Explanations

    enhanced increased

    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
     enhanced
    -1.94
     increased
    -1.80
    increased
    -1.71
     improved
    -1.70
    enhanced
    -1.68
    improved
    -1.55
    Increased
    -1.52
    Enhanced
    -1.52
     expanded
    -1.49
     heightened
    -1.46
    POSITIVE LOGITS
     by
    0.78
     past
    0.63
     its
    0.57
    EndProject
    0.55
     my
    0.54
     to
    0.53
    mybatisplus
    0.52
    awaiter
    0.52
    WebElementEntity
    0.52
     upon
    0.49
    Activations Density 0.084%

    No Known Activations