© 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. 40521
    Prev
    Next
    INDEX
    Explanations

    GOP

    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
     Theſe
    -1.16
     Reſ
    -1.05
     itſelf
    -1.05
     Anſ
    -1.00
     Majefty
    -0.97
     doubtnut
    -0.96
     myſelf
    -0.96
     étoit
    -0.94
     ainfi
    -0.94
     étoient
    -0.93
    POSITIVE LOGITS
     a
    1.21
     not
    1.08
     the
    1.07
     so
    0.93
     an
    0.91
     
    0.91
     far
    0.85
     "
    0.82
     “
    0.81
     more
    0.79
    Activations Density 0.003%

    No Known Activations