© 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. 0-CLT-HP
    7. 97739
    Prev
    Next
    INDEX
    Explanations

    principal

    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
     principal
    -1.07
    principal
    -1.02
     principals
    -0.94
    en
    -0.74
     estimés
    -0.73
    princip
    -0.73
     principale
    -0.68
     v
    -0.68
    Principal
    -0.67
     principales
    -0.62
    POSITIVE LOGITS
     Efq
    0.69
    GEBURTSDATUM
    0.66
    umque
    0.60
    izer
    0.57
    Minist
    0.57
    ритори
    0.56
    izing
    0.56
     mutate
    0.56
    ſelf
    0.55
     myſelf
    0.55
    Activations Density 0.104%

    No Known Activations