© 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. 3251
    Prev
    Next
    INDEX
    Explanations

    Courtship and mating

    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
    SourceChecksum
    -0.71
    httphttps
    -0.69
    Clik
    -0.59
    prüche
    -0.59
    CloseOperation
    -0.55
    usahaan
    -0.55
    ues
    -0.53
    Itoa
    -0.52
    BURGH
    -0.51
    lí
    -0.50
    POSITIVE LOGITS
     rituals
    0.79
     ritual
    0.64
    OrBuilder
    0.59
     StatefulWidget
    0.57
     customs
    0.57
    المناصب
    0.56
    WriteBarrier
    0.53
     dances
    0.52
     dance
    0.50
     JpaRepository
    0.49
    Activations Density 0.002%

    No Known Activations