© 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. 44154
    Prev
    Next
    INDEX
    Explanations

    orte

    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
    vings
    -0.71
    orte
    -0.66
    neros
    -0.60
    inga
    -0.59
     ruinas
    -0.54
    elin
    -0.53
    ագրություններ
    -0.53
    creen
    -0.50
    ά
    -0.50
    échelle
    -0.50
    POSITIVE LOGITS
     myſelf
    0.71
     himſelf
    0.69
     pleaſure
    0.67
     themſelves
    0.65
     Efq
    0.64
     CreateTagHelper
    0.60
     تضيفلها
    0.59
    VIRGO
    0.59
     itſelf
    0.58
     fevere
    0.57
    Activations Density 1.480%

    No Known Activations