© 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. 38991
    Prev
    Next
    INDEX
    Explanations

    beyond

    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
     without
    -0.83
     adults
    -0.79
     zonder
    -0.69
    without
    -0.67
     tanpa
    -0.66
     according
    -0.65
     adultos
    -0.65
     beyond
    -0.60
     Adults
    -0.60
     adultes
    -0.60
    POSITIVE LOGITS
     CreateTagHelper
    0.84
     дописавши
    0.79
     Paglinawan
    0.78
    IndentedString
    0.76
    addPreferredGap
    0.74
    IntoConstraints
    0.71
    ophytes
    0.70
    ParallelGroup
    0.69
    neath
    0.68
    featureID
    0.68
    Activations Density 1.203%

    No Known Activations