© 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. 20-CLT-HP
    4. 74888
    Prev
    Next
    INDEX
    Explanations

    industry and society

    np_max-act-logits · 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
    
    -0.93
     متعلقه
    -0.73
    makeConstraints
    -0.63
     bezeichneter
    -0.63
    原始内容存档于
    -0.62
    IMPORTED
    -0.60
    esModule
    -0.58
    Personendaten
    -0.58
    AndroidJUnit
    -0.56
    хьтан
    -0.54
    POSITIVE LOGITS
     baron
    0.83
     ty
    0.75
     barons
    0.69
     magn
    0.63
     executive
    0.61
     country
    0.60
    man
    0.55
     capital
    0.53
     mans
    0.53
    men
    0.52
    Activations Density 0.000%

    No Known Activations