© 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. 46188
    Prev
    Next
    INDEX
    Explanations

    introduce

    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
     enfans
    -0.70
    ArgsConstructor
    -0.63
     ferons
    -0.63
     fermés
    -0.60
     vostri
    -0.59
    følgelig
    -0.58
     numériques
    -0.58
     nationaux
    -0.58
     importanza
    -0.57
     escuro
    -0.56
    POSITIVE LOGITS
    قایناق‌لار
    0.58
     zewnętrzne
    0.56
    tamol
    0.55
     Vishnu
    0.54
     kaarangay
    0.54
     '');
    0.53
     farmed
    0.52
     doorstep
    0.52
     cows
    0.52
     new
    0.52
    Activations Density 0.003%

    No Known Activations