© 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. 97376
    Prev
    Next
    INDEX
    Explanations

    inv

    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
     demonstrated
    -0.64
    rrggbb
    -0.61
     exerted
    -0.58
     awoke
    -0.57
     adquirido
    -0.54
     resumed
    -0.54
     raggiunto
    -0.54
     occupé
    -0.53
     ottenuto
    -0.52
     cérami
    -0.52
    POSITIVE LOGITS
    الدراسه
    0.60
    exposure
    0.60
    Personendaten
    0.59
     NSCoder
    0.56
    pron
    0.55
    shel
    0.54
     Monticello
    0.54
    scared
    0.52
    PMailer
    0.52
     }</
    0.52
    Activations Density 0.155%

    No Known Activations