© 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. 45797
    Prev
    Next
    INDEX
    Explanations

    eth

    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
    MigrationBuilder
    -0.69
    apunov
    -0.64
    AddHtmlAttribute
    -0.62
    ArgsConstructor
    -0.62
     blow
    -0.58
     שוליים
    -0.58
     blows
    -0.57
     gawas
    -0.56
    NTIS
    -0.55
    MemoryWarning
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.66
    ThroughAttribute
    0.54
    katapos
    0.48
     démocr
    0.48
     normaux
    0.47
     colorés
    0.47
     partenza
    0.47
     stället
    0.47
     récentes
    0.46
    ulman
    0.45
    Activations Density 0.058%

    No Known Activations