© 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. 5-CLT-HP
    7. 2349
    Prev
    Next
    INDEX
    Explanations

    be

    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
    onAttach
    -0.75
     gynhyrchwyd
    -0.72
    mybatisplus
    -0.70
     חיצוניים
    -0.69
     itſelf
    -0.69
    Tikang
    -0.65
    Autoritní
    -0.64
    httphttps
    -0.63
     Waray
    -0.63
     smtplib
    -0.62
    POSITIVE LOGITS
     great
    0.75
     cool
    0.71
     awesome
    0.65
     coolest
    0.59
     fun
    0.54
    awesome
    0.54
     AWESOME
    0.53
     cooler
    0.52
    verlauf
    0.52
     amazing
    0.51
    Activations Density 0.007%

    No Known Activations