© 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. 94523
    Prev
    Next
    INDEX
    Explanations

    Code/text snippets

    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
     <<<<<<<<<<<<<<
    -0.66
    <bos>
    -0.64
     InputDecoration
    -0.59
    keyColumn
    -0.57
     BoxDecoration
    -0.52
     saites
    -0.49
    AndroidJUnit
    -0.48
    اظ
    -0.47
    őség
    -0.46
     Wikispecies
    -0.45
    POSITIVE LOGITS
     виправивши
    0.57
    Компания
    0.54
    ]!='
    0.53
    sidemargin
    0.53
    ^(@)
    0.52
    entsch
    0.52
     judiciaire
    0.51
     cinéma
    0.51
    herjee
    0.50
     Bár
    0.50
    Activations Density 0.010%

    No Known Activations