© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93522
    Prev
    Next
    INDEX
    Explanations

    collection

    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
    collect
    -1.22
    collected
    -1.19
    collection
    -1.15
     collecting
    -1.07
     collect
    -1.05
     collected
    -1.05
     Collecting
    -1.05
    COLLECTION
    -1.03
    Collecting
    -1.03
    collecting
    -1.02
    POSITIVE LOGITS
     +
    0.59
     plus
    0.54
     can
    0.50
     or
    0.48
     cherchez
    0.45
     for
    0.44
    !
    0.44
     детства
    0.43
     &
    0.43
     could
    0.43
    Activations Density 0.352%

    No Known Activations