© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3458
    Prev
    Next
    INDEX
    Explanations

    decades, time periods

    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
    المكان
    -0.79
    msgTypes
    -0.74
     विश्वसनीयता
    -0.72
    ]));
    
    -0.70
    AccessorTable
    -0.69
     كومونز
    -0.69
    exitRule
    -0.69
    FieldNumber
    -0.68
     ujednoznacz
    -0.68
    ConstraintMaker
    -0.68
    POSITIVE LOGITS
     Au
    0.40
     setContent
    0.39
    phantom
    0.39
    Cat
    0.38
     Ghe
    0.38
    Beste
    0.38
     gepubliceerd
    0.37
    Tbl
    0.37
     Мексичка
    0.37
     pere
    0.37
    Activations Density 0.002%

    No Known Activations