© 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. 91043
    Prev
    Next
    INDEX
    Explanations

    tmp

    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
     Berkeley
    -0.74
    Berkeley
    -0.70
     Baltimore
    -0.60
    arsus
    -0.59
     tmp
    -0.57
    trup
    -0.57
     Re
    -0.55
     ar
    -0.53
    tmp
    -0.52
     Ar
    -0.52
    POSITIVE LOGITS
     سكانية
    0.84
     itſelf
    0.80
     épaules
    0.74
     cardiaque
    0.74
    Хьажоргаш
    0.73
     ―――――
    0.71
     raiſ
    0.71
     leaſt
    0.70
     Мексичка
    0.68
     ſche
    0.68
    Activations Density 0.183%

    No Known Activations