© 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. 5-CLT-HP
    7. 99
    Prev
    Next
    INDEX
    Explanations

    hand

    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
     to
    -1.91
     kepada
    -1.05
    tothe
    -0.91
    到
    -0.90
    to
    -0.86
    ToUser
    -0.79
     thereto
    -0.77
    DataTo
    -0.71
     tot
    -0.70
    ToList
    -0.68
    POSITIVE LOGITS
     kasarigan
    0.67
    awtextra
    0.64
    HostException
    0.62
    IntoConstraints
    0.60
    mbler
    0.56
    IContainer
    0.56
    ücks
    0.54
    tangentMode
    0.53
     considérons
    0.52
     useAppContext
    0.52
    Activations Density 0.004%

    No Known Activations