© 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. 39875
    Prev
    Next
    INDEX
    Explanations

    smoothie

    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
     MonoBehaviour
    -0.85
     defaultstate
    -0.79
    GeneratedValue
    -0.76
    HtmlAttribute
    -0.76
     thither
    -0.75
     caldera
    -0.72
    SourceChecksum
    -0.69
     periphery
    -0.69
     propOrder
    -0.69
     leſs
    -0.68
    POSITIVE LOGITS
    ized
    0.81
    ization
    0.71
    ize
    0.71
    IZATION
    0.61
    izing
    0.60
    isation
    0.59
    ist
    0.59
    ه
    0.58
    ity
    0.57
    izer
    0.57
    Activations Density 0.071%

    No Known Activations