© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    instructions or advice

    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
    IntoConstraints
    -0.55
     namelijk
    -0.54
     виправивши
    -0.53
     nemlig
    -0.52
    '):
    -0.51
     autorytatywna
    -0.51
     gouvernements
    -0.49
     prisonniers
    -0.49
     ifrån
    -0.49
    ]")]
    -0.48
    POSITIVE LOGITS
    hardy
    0.58
     characteristic
    0.57
     uſed
    0.57
    serviceWorker
    0.56
    ering
    0.56
    fitting
    0.55
     thoughtful
    0.55
     amenities
    0.54
     greateſt
    0.54
     hardy
    0.54
    Activations Density 0.012%

    No Known Activations