© 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. 0-CLT-HP
    7. 90684
    Prev
    Next
    INDEX
    Explanations

    high resolution

    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
     forming
    -0.72
     weak
    -0.71
     mild
    -0.65
    mild
    -0.63
     Forming
    -0.62
     Weak
    -0.60
     weaker
    -0.59
     getRule
    -0.57
     faible
    -0.57
     weakly
    -0.57
    POSITIVE LOGITS
     HasFactory
    0.66
     kasarigan
    0.65
     Мексичка
    0.62
    Tembelea
    0.54
    TagHelpers
    0.52
    ISupport
    0.51
    IRUS
    0.51
    SequentialGroup
    0.50
    ὖ
    0.49
    AccessFile
    0.49
    Activations Density 1.491%

    No Known Activations