Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39503
    Prev
    Next
    INDEX
    Explanations

    Minecraft

    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
    ane
    -0.84
    imeter
    -0.63
    ANE
    -0.62
    сылкі
    -0.54
    elas
    -0.54
     Minecraft
    -0.52
    ement
    -0.52
    ama
    -0.52
    ⓘ
    -0.51
    mane
    -0.50
    POSITIVE LOGITS
     للمعارف
    0.75
     كومونز
    0.70
    skosten
    0.70
     AssemblyTitle
    0.69
    PhysRevD
    0.61
     незавершена
    0.60
     ThemeData
    0.60
     Bourgoin
    0.60
    ség
    0.59
    InitVars
    0.57
    Activations Density 0.283%

    No Known Activations