© 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. 1-CLT-HP
    7. 45657
    Prev
    Next
    INDEX
    Explanations

    successful/success

    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
     facie
    -0.60
     jäm
    -0.59
     forskjellige
    -0.57
     câte
    -0.52
     vanske
    -0.50
     forskellige
    -0.49
     länge
    -0.49
     rosse
    -0.48
     nød
    -0.48
     skydd
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
    rungsseite
    0.77
    Cyfeiriadau
    0.72
     propOrder
    0.72
    StoryboardSegue
    0.70
    UnusedPrivate
    0.68
    SourceChecksum
    0.64
    full
    0.63
     Comprometido
    0.61
     ویکی‌پدی
    0.60
    Activations Density 0.022%

    No Known Activations