© 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. 96106
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    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
    BeginContext
    -0.91
    Vidite
    -0.81
     تضيفلها
    -0.76
    PreferredItem
    -0.74
    Datuak
    -0.71
    EDEFAULT
    -0.71
    Попис
    -0.71
    AndroidJUnit
    -0.68
    Atsauces
    -0.68
    Demografia
    -0.67
    POSITIVE LOGITS
    Snackbar
    0.42
    Abr
    0.41
    Filmographie
    0.39
    ỗng
    0.38
     "',
    0.37
    плек
    0.36
    cba
    0.36
     Doble
    0.35
    aman
    0.35
     concor
    0.35
    Activations Density 0.002%

    No Known Activations