© 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. 5-CLT-HP
    7. 984
    Prev
    Next
    INDEX
    Explanations

    convert

    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
     فريبيس
    -0.63
     leaſt
    -0.63
     ainfi
    -0.62
     myſelf
    -0.62
     ſeveral
    -0.62
     éché
    -0.60
     purpoſe
    -0.60
     invokingState
    -0.60
     glisser
    -0.60
     ſmall
    -0.59
    POSITIVE LOGITS
    SpringBootTest
    0.52
    WillAppear
    0.50
    脚注の使い方
    0.50
     >=",
    0.47
    הערות
    0.45
     expédié
    0.42
    xaml
    0.42
    Билгалдахарш
    0.41
    DeleteMapping
    0.38
    RadioGroup
    0.38
    Activations Density 0.000%

    No Known Activations