© 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. 4485
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    :\/\/
    -0.57
     snippetHide
    -0.57
    )=>{
    -0.56
    writeFieldEnd
    -0.56
     mu
    -0.51
    BAU
    -0.50
     of
    -0.50
    /**
    -0.48
    intios
    -0.48
    mybatisplus
    -0.47
    POSITIVE LOGITS
     Normdatei
    0.69
    Память
    0.64
    nodeValue
    0.57
     myſelf
    0.57
     Aún
    0.56
     zirc
    0.56
     Kości
    0.56
    RectangleBorder
    0.55
     purpoſe
    0.54
     δὲ
    0.53
    Activations Density 0.003%

    No Known Activations