© 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. 96221
    Prev
    Next
    INDEX
    Explanations

    biological substances

    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
    IVEREF
    -0.80
    GEBURTSDATUM
    -0.79
    EDEFAULT
    -0.76
    StructEnd
    -0.74
    DeleteBehavior
    -0.69
    fromnode
    -0.67
    complexContent
    -0.66
    CloseOperation
    -0.65
    ьаж
    -0.65
     تضيفلها
    -0.65
    POSITIVE LOGITS
     églises
    0.57
    èvent
    0.52
    sill
    0.46
    hadores
    0.46
     genommen
    0.45
     szabály
    0.44
     personnaliser
    0.44
    permum
    0.43
     aktivitet
    0.43
     novità
    0.43
    Activations Density 0.028%

    No Known Activations