© 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. 92679
    Prev
    Next
    INDEX
    Explanations

    straight

    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
     straight
    -1.22
     directly
    -1.12
    straight
    -0.92
     direttamente
    -0.92
     langsung
    -0.91
    Straight
    -0.90
     diretamente
    -0.90
     directement
    -0.90
     directamente
    -0.88
     Straight
    -0.81
    POSITIVE LOGITS
    risen
    0.70
     Italijanski
    0.56
     فريبيس
    0.54
     dAtA
    0.53
     Pew
    0.53
     ITU
    0.52
    millions
    0.52
     pros
    0.51
     Suez
    0.50
     Zaman
    0.50
    Activations Density 0.083%

    No Known Activations