© 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. 1-CLT-HP
    4. 849
    Prev
    Next
    INDEX
    Explanations

    Auschwitz

    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
    locaust
    -1.09
    ocere
    -0.53
    AndEndTag
    -0.53
     Holocaust
    -0.52
    dbc
    -0.52
     bağlantılar
    -0.50
    RenderAtEndOf
    -0.48
    
    -0.47
     getSource
    -0.46
     substance
    -0.44
    POSITIVE LOGITS
    клопе
    0.65
     становника
    0.64
    s
    0.58
    blico
    0.56
     CreateTagHelper
    0.55
     头像
    0.54
     Jej
    0.54
    mutlich
    0.53
    Datuak
    0.52
    favourable
    0.52
    Activations Density 0.014%

    No Known Activations