© 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. 4-CLT-HP
    4. 2530
    Prev
    Next
    INDEX
    Explanations

    "short for" descriptions

    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
     Combien
    -0.50
    
    -0.46
    Havolalar
    -0.45
    ECES
    -0.45
    tencent
    -0.45
    !("{
    -0.45
     mdi
    -0.44
    SpringBootTest
    -0.44
     lenker
    -0.43
    Enllaços
    -0.42
    POSITIVE LOGITS
    InteropServices
    0.60
    himovic
    0.57
     Romana
    0.56
     kaynağından
    0.53
    Geografía
    0.52
    mania
    0.52
    Datuak
    0.52
     اكتوبر
    0.52
     Kön
    0.51
     ISNI
    0.51
    Activations Density 0.002%

    No Known Activations