© 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. 43996
    Prev
    Next
    INDEX
    Explanations

    local news reports

    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
    missions
    -0.88
    stown
    -0.73
     admitted
    -0.62
    mitted
    -0.58
    MISSION
    -0.56
    JNIEnv
    -0.56
    credited
    -0.55
     وتسجيلات
    -0.55
    mission
    -0.50
    laka
    -0.50
    POSITIVE LOGITS
    ForTesting
    0.60
     üzere
    0.60
    zzar
    0.58
     calum
    0.57
    phant
    0.56
    ạp
    0.56
    tuta
    0.56
     Sahel
    0.55
     supper
    0.54
     Fielding
    0.54
    Activations Density 1.599%

    No Known Activations