© 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. 5-CLT-HP
    7. 97347
    Prev
    Next
    INDEX
    Explanations

    special

    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
     hikers
    -0.55
     bureaucrats
    -0.52
    ushchev
    -0.51
    wissenschaften
    -0.50
     administr
    -0.50
    almost
    -0.49
    UITableView
    -0.49
     AspNetCore
    -0.49
     administrators
    -0.48
    getExtras
    -0.48
    POSITIVE LOGITS
    INCREF
    0.63
     estimés
    0.57
     long
    0.57
     prepared
    0.55
     designed
    0.53
     виправивши
    0.52
     calculées
    0.51
    KURZBESCHREIBUNG
    0.50
    جمعیت
    0.49
    بوابة
    0.48
    Activations Density 0.002%

    No Known Activations