© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1066
    Prev
    Next
    INDEX
    Explanations

    God

    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
    AddTagHelper
    -0.57
     ویکی‌پدیا
    -0.53
    MessageTagHelper
    -0.52
    schwe
    -0.48
    bukkit
    -0.48
     zast
    -0.47
     solidity
    -0.47
    Quack
    -0.47
    ]")]
    -0.47
    YTA
    -0.47
    POSITIVE LOGITS
    новништво
    0.69
    tvguidetime
    0.54
    PYX
    0.54
    Зноскі
    0.53
     متعلقه
    0.52
     will
    0.52
    TableField
    0.51
     bụ
    0.47
     externi
    0.47
    ajemy
    0.47
    Activations Density 0.002%

    No Known Activations