© 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. 90594
    Prev
    Next
    INDEX
    Explanations

    source

    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
    assertions
    -0.55
    iff
    -0.51
    …
    -0.47
    </em>
    -0.45
    ATTENTION
    -0.44
     the
    -0.44
    IFF
    -0.43
    ja
    -0.43
    勝手
    -0.43
    toBeDefined
    -0.42
    POSITIVE LOGITS
     propOrder
    0.88
    Personendaten
    0.81
     CreateTagHelper
    0.79
     Seeder
    0.78
     للاسماء
    0.78
    HideFlags
    0.73
    ंदीखरीदारी
    0.72
     purpoſe
    0.71
    multer
    0.71
     themſelves
    0.69
    Activations Density 0.193%

    No Known Activations