© 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. 0-CLT-HP
    7. 41053
    Prev
    Next
    INDEX
    Explanations

    Okay

    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
     bend
    -0.60
     ta
    -0.56
     li
    -0.48
    ן
    -0.47
     mutation
    -0.46
     lo
    -0.44
     war
    -0.44
     resigned
    -0.43
    mutant
    -0.42
     los
    -0.42
    POSITIVE LOGITS
     myſelf
    1.10
     Monfieur
    1.10
     himſelf
    1.08
     themſelves
    1.07
     Diſ
    1.07
     Anſ
    1.07
     Houſe
    1.05
     itſelf
    1.05
     Majefty
    1.05
     ſeveral
    1.02
    Activations Density 0.672%

    No Known Activations