© 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. 5-CLT-HP
    4. 3084
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    principalTable
    -0.62
    bumptech
    -0.44
    اته
    -0.42
    стат
    -0.38
    eventbus
    -0.38
     Integrity
    -0.37
    зыка
    -0.36
     integrity
    -0.36
    CodedInputStream
    -0.36
    ЛЯ
    -0.35
    POSITIVE LOGITS
    ChildScrollView
    0.75
    ⓧ
    0.75
    IndentedString
    0.73
     الرياضيه
    0.69
    doria
    0.66
    таратура
    0.65
    原始内容存档于
    0.65
    SBATCH
    0.63
    DrawerToggle
    0.63
    러나
    0.63
    Activations Density 0.001%

    No Known Activations