© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40471
    Prev
    Next
    INDEX
    Explanations

    Workshop

    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
     traditional
    -1.16
     machine
    -1.10
     Traditional
    -0.95
     traditionnelle
    -0.90
    Traditional
    -0.89
    machine
    -0.88
     tradizionale
    -0.88
     traditionnels
    -0.85
     machines
    -0.84
    traditional
    -0.82
    POSITIVE LOGITS
    aarrggbb
    0.83
    脚注の使い方
    0.82
     Baillargeon
    0.75
    #+#
    0.74
    adaptiveStyles
    0.71
     snippetHide
    0.71
     MainAxisSize
    0.71
     sumpay
    0.71
    +#+#
    0.71
    DeleteBehavior
    0.69
    Activations Density 0.093%

    No Known Activations