© 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. 5-CLT-HP
    7. 94392
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
     exactly
    -0.61
     exakt
    -0.49
    Exactly
    -0.49
     brancas
    -0.48
     precies
    -0.48
     Exactly
    -0.47
    exactly
    -0.46
     esattamente
    -0.46
     compétences
    -0.46
     eneste
    -0.44
    POSITIVE LOGITS
     BitmapFactory
    0.72
    ousands
    0.72
     للمعارف
    0.69
    verwijspagina
    0.69
     препратки
    0.69
    fois
    0.66
    galo
    0.65
    ]<<"
    0.64
    efois
    0.60
    antart
    0.59
    Activations Density 0.003%

    No Known Activations