© 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. 4-CLT-HP
    7. 4587
    Prev
    Next
    INDEX
    Explanations

    quite

    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
    脚注の使い方
    -0.69
    RuleContext
    -0.54
    BeginInit
    -0.51
    -------------</
    -0.51
    stdio
    -0.50
    曖昧さ回避
    -0.50
     AppDelegate
    -0.50
     tsk
    -0.48
    roek
    -0.48
     didReceive
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.75
    bootstrapcdn
    0.64
    mybatisplus
    0.60
    ubel
    0.55
     belli
    0.53
    adpleegd
    0.52
     Dernière
    0.52
     darbo
    0.52
    visející
    0.51
     متعلقه
    0.50
    Activations Density 0.004%

    No Known Activations