© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46042
    Prev
    Next
    INDEX
    Explanations

    operands

    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
     ostavi
    -1.00
     Praxis
    -0.93
    Praxis
    -0.85
     praxis
    -0.79
    principalColumn
    -0.79
    SBATCH
    -0.76
     resourceCulture
    -0.73
    rawDesc
    -0.71
    Personensuche
    -0.71
     autorytatywna
    -0.71
    POSITIVE LOGITS
    ly
    0.45
    card
    0.45
    cs
    0.40
    Климат
    0.40
    падает
    0.39
     Breite
    0.39
    gly
    0.38
    ことができました
    0.38
    kunjung
    0.38
    cas
    0.37
    Activations Density 0.039%

    No Known Activations