© 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. 96308
    Prev
    Next
    INDEX
    Explanations

    condition

    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
    ształ
    -0.50
    arakhand
    -0.49
     naturen
    -0.49
    Sản
    -0.46
     DataTypes
    -0.45
    RegisterType
    -0.44
    Kaynakça
    -0.44
     оригіналу
    -0.44
    UserScript
    -0.43
    igsaw
    -0.43
    POSITIVE LOGITS
     of
    0.82
    ings
    0.63
    IonicModule
    0.62
    centralwidget
    0.61
    ReusableCell
    0.60
    StoryboardSegue
    0.60
     BoxDecoration
    0.60
    adaptiveStyles
    0.60
    ning
    0.59
     whereof
    0.59
    Activations Density 0.003%

    No Known Activations