© 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. 45072
    Prev
    Next
    INDEX
    Explanations

    efficient

    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
     efficient
    -1.05
     efficiently
    -0.98
     eficientes
    -0.88
    efficient
    -0.83
     efficacement
    -0.82
    دانشنامهٔ
    -0.82
     eficiente
    -0.82
     efficaces
    -0.82
     efficace
    -0.81
    Efficient
    -0.77
    POSITIVE LOGITS
    DataAnnotations
    0.48
     IFA
    0.47
    be
    0.45
    ca
    0.44
    ScreenState
    0.43
     Flor
    0.42
     departments
    0.41
    ci
    0.41
    m
    0.41
     logistic
    0.40
    Activations Density 0.031%

    No Known Activations