© 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. 4-CLT-HP
    7. 4375
    Prev
    Next
    INDEX
    Explanations

    Colombian

    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
     invokingState
    -0.88
     disponibilités
    -0.65
    SPATH
    -0.63
    ंदीखरीदारी
    -0.63
    RunWith
    -0.59
     tabPage
    -0.59
    دانشنامهٔ
    -0.58
     Мексичка
    -0.56
    Datuak
    -0.55
    SqlClient
    -0.53
    POSITIVE LOGITS
    ian
    0.68
    Exchange
    0.58
    iad
    0.56
    matchCondition
    0.56
     Exchange
    0.53
    IAN
    0.50
    expo
    0.48
     Exposition
    0.47
     inappropriés
    0.47
    اضر
    0.47
    Activations Density 0.001%

    No Known Activations