© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42626
    Prev
    Next
    INDEX
    Explanations

    collect

    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
     collection
    -2.27
    collection
    -2.20
     collected
    -2.14
     collect
    -2.08
     collecting
    -2.08
     Collection
    -2.05
    collect
    -2.03
    collected
    -2.03
    Collection
    -1.99
     collections
    -1.90
    POSITIVE LOGITS
    MLLoader
    0.59
    ğu
    0.50
    はじめに
    0.50
     acetic
    0.49
     Decode
    0.48
     syllables
    0.47
     Callahan
    0.47
    enterOuterAlt
    0.47
    SharedDtor
    0.46
    portál
    0.46
    Activations Density 0.080%

    No Known Activations