© 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. 91133
    Prev
    Next
    INDEX
    Explanations

    Amid

    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
    permum
    -0.65
    expression
    -0.54
    aternary
    -0.40
    reportWebVitals
    -0.40
     p
    -0.39
    OnInit
    -0.38
    umn
    -0.38
    ornis
    -0.38
     l
    -0.37
    平台
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.86
    st
    0.84
     myſelf
    0.82
    sizeCache
    0.81
     ExecuteAsync
    0.79
     مرئيه
    0.76
     purpoſe
    0.76
     يتيمه
    0.75
    )=>{
    0.75
     diſt
    0.74
    Activations Density 1.580%

    No Known Activations