© 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. 1-CLT-HP
    7. 11788
    Prev
    Next
    INDEX
    Explanations

    y

    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
     rêves
    -0.76
     démocr
    -0.74
     dieux
    -0.71
     scolaires
    -0.68
     négociations
    -0.68
     normaux
    -0.67
     varandra
    -0.66
     traités
    -0.65
     découver
    -0.65
     chré
    -0.64
    POSITIVE LOGITS
    AndEndTag
    0.65
    SpringBootTest
    0.60
    сылкі
    0.60
    الدراسه
    0.59
    QMetaType
    0.57
     figures
    0.57
    cshtml
    0.56
    findpost
    0.56
    principalColumn
    0.55
     oprot
    0.54
    Activations Density 0.029%

    No Known Activations