© 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. 4-CLT-HP
    7. 2615
    Prev
    Next
    INDEX
    Explanations

    Bahadur

    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
     صوتيه
    -0.40
     fale
    -0.40
    insular
    -0.39
    lero
    -0.39
    lorette
    -0.38
     automatiques
    -0.38
    höhe
    -0.38
     cumbre
    -0.38
    UseVisualStyle
    -0.36
    ızı
    -0.36
    POSITIVE LOGITS
    ThemeOverlay
    0.79
    ](#
    0.76
    __':
    0.75
    पया
    0.73
    abstractmethod
    0.68
    таратура
    0.66
     '\\;'
    0.63
    تقاوى
    0.63
     uric
    0.62
     StringTokenizer
    0.61
    Activations Density 0.002%

    No Known Activations