© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    refugees

    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
     buried
    -0.47
     hidden
    -0.47
     burying
    -0.44
     hid
    -0.42
     stayed
    -0.39
    clusion
    -0.39
     bury
    -0.39
    hidden
    -0.39
     fanns
    -0.39
     occlusion
    -0.38
    POSITIVE LOGITS
    migrationBuilder
    0.84
     ویکی‌پدیای
    0.81
     ***!
    0.81
     dAtA
    0.76
    bewerken
    0.74
    +:+
    0.73
     onAnimation
    0.71
    ItemBackground
    0.70
    AndroidJUnit
    0.70
    Demografia
    0.69
    Activations Density 0.001%

    No Known Activations