© 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. 20-CLT-HP
    7. 74688
    Prev
    Next
    INDEX
    Explanations

    absence

    np_max-act-logits · 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
     CreateTagHelper
    -0.98
     للمعارف
    -0.80
     مرئيه
    -0.78
    脚注の使い方
    -0.75
     ModelExpression
    -0.74
     Drink
    -0.74
     &___
    -0.71
     utafitiHapana
    -0.71
     HttpNotFound
    -0.71
    +#+#
    -0.69
    POSITIVE LOGITS
     clean
    0.54
     plain
    0.51
     clear
    0.48
     non
    0.46
     free
    0.45
     чи
    0.44
     un
    0.42
    Facades
    0.41
     pure
    0.41
     cool
    0.40
    Activations Density 0.001%

    No Known Activations