© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45435
    Prev
    Next
    INDEX
    Explanations

    brass

    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
     myſelf
    -1.11
     itſelf
    -1.08
     themſelves
    -1.02
     ainfi
    -0.97
     ſtate
    -0.96
     avoient
    -0.95
     purpoſe
    -0.94
     Jefus
    -0.92
     ſta
    -0.92
     ſeveral
    -0.92
    POSITIVE LOGITS
    es
    0.62
    er
    0.57
     in
    0.57
    e
    0.57
    y
    0.56
     last
    0.54
     la
    0.54
     ac
    0.54
    ic
    0.53
    u
    0.53
    Activations Density 1.512%

    No Known Activations