© 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. 96391
    Prev
    Next
    INDEX
    Explanations

    and or

    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
     Roskov
    -0.59
     autorytatywna
    -0.58
     незавершена
    -0.56
    thâu
    -0.55
    出版年
    -0.54
     <=",
    -0.54
     مشين
    -0.54
    bewerken
    -0.54
    usitis
    -0.54
     kasarigan
    -0.52
    POSITIVE LOGITS
     MainAxisSize
    0.65
     interactive
    0.52
    interactive
    0.50
     choć
    0.50
     cref
    0.48
     situato
    0.48
     magari
    0.46
    IBOutlet
    0.46
     quizá
    0.46
     /
    0.46
    Activations Density 0.005%

    No Known Activations