© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    engine

    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
    Engine
    -0.98
    engine
    -0.90
     engine
    -0.79
     Engine
    -0.72
    Fort
    -0.71
     Fort
    -0.70
    tree
    -0.68
    ENGINE
    -0.67
     ENGINE
    -0.61
     FORT
    -0.58
    POSITIVE LOGITS
     Efq
    1.23
     itſelf
    1.16
     myſelf
    1.14
     themſelves
    1.03
     purpoſe
    1.02
     Monfieur
    1.02
     Houſe
    1.01
     Jefus
    0.98
     himſelf
    0.97
     doubtnut
    0.96
    Activations Density 0.286%

    No Known Activations