© 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. 5-CLT-HP
    7. 1973
    Prev
    Next
    INDEX
    Explanations

    quite

    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
     offend
    -0.50
     referenties
    -0.49
    CppMethod
    -0.48
     dAtA
    -0.47
    twimg
    -0.46
    زار
    -0.46
     المتحدة
    -0.46
     betweenstory
    -0.46
     AppCompatTheme
    -0.45
    unite
    -0.45
    POSITIVE LOGITS
     surla
    0.69
    Scape
    0.56
    řevě
    0.52
     مواليد
    0.52
     downloaded
    0.50
    ільки
    0.50
    MLLoader
    0.49
     Recuperado
    0.48
    StatusBadRequest
    0.48
     المعيارى
    0.48
    Activations Density 0.008%

    No Known Activations