© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    gave

    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
     '\\;'
    -0.60
    entlig
    -0.49
    ンダ
    -0.48
    createObject
    -0.48
    Repeat
    -0.48
    Autoritní
    -0.47
     gu
    -0.47
    later
    -0.46
    chium
    -0.46
    今度は
    -0.45
    POSITIVE LOGITS
    IsMutable
    0.79
     发表于
    0.60
    Билгалдахарш
    0.59
    ActionCreators
    0.56
     StatefulWidget
    0.55
    tanleria
    0.54
    CrossRef
    0.52
     colectiva
    0.51
     configureStore
    0.50
     it
    0.50
    Activations Density 0.001%

    No Known Activations