© 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. 1-CLT-HP
    4. 13507
    Prev
    Next
    INDEX
    Explanations

    Co

    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
     co
    -0.68
     coö
    -0.63
     Unger
    -0.58
     layers
    -0.58
     dignity
    -0.57
    WebElementEntity
    -0.54
     statement
    -0.54
     isolation
    -0.54
     organ
    -0.53
     driving
    -0.53
    POSITIVE LOGITS
     GenerationType
    0.49
     ActiveRecord
    0.48
     ujednoznacz
    0.47
    istani
    0.46
    =*/
    0.43
    Sign
    0.42
    ImageContext
    0.42
    ons
    0.41
     chré
    0.41
    BSITE
    0.41
    Activations Density 0.028%

    No Known Activations