© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    years

    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
    ophyte
    -1.63
    ophytes
    -1.28
    saraba
    -0.60
     bezeichneter
    -0.58
    AddHtmlAttribute
    -0.58
    Widths
    -0.56
     parvenir
    -0.55
     resourceCulture
    -0.55
     发表于
    -0.52
     تضيفلها
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.53
    obe
    0.53
    omenti
    0.48
    minecraftforge
    0.48
     DNA
    0.48
     Turch
    0.48
     gyrus
    0.47
    besos
    0.46
     Fo
    0.46
     OnTriggerEnter
    0.46
    Activations Density 0.038%

    No Known Activations