© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1229
    Prev
    Next
    INDEX
    Explanations

    White House, politics

    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
     House
    -0.93
     HOUSE
    -0.59
    House
    -0.57
     Miller
    -0.52
     hem
    -0.51
     house
    -0.49
    house
    -0.49
    hem
    -0.46
     Maison
    -0.46
     maison
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    1.08
     avoient
    0.94
     étoient
    0.92
     hâte
    0.91
     doInBackground
    0.90
    BeginContext
    0.90
     Shaksp
    0.89
    DockStyle
    0.89
     vectorielles
    0.88
    berdayakan
    0.87
    Activations Density 0.511%

    No Known Activations