© 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. 90890
    Prev
    Next
    INDEX
    Explanations

    anytime

    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
     ever
    -1.71
    Ever
    -1.32
    ever
    -1.30
     EVER
    -1.27
     Ever
    -1.23
    EVER
    -1.05
     anytime
    -0.94
     Anytime
    -0.90
     jemals
    -0.88
     anywhere
    -0.85
    POSITIVE LOGITS
    SizeMode
    0.64
     متعلقه
    0.56
    ghar
    0.54
     ویکی‌پدیای
    0.54
     مشين
    0.54
    żyć
    0.53
    thing
    0.53
    rimp
    0.53
    ρασ
    0.52
     perhaps
    0.52
    Activations Density 0.033%

    No Known Activations