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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43250
    Prev
    Next
    INDEX
    Explanations

    of

    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
     or
    -1.81
     или
    -1.11
     atau
    -0.96
     eller
    -0.95
     a
    -0.94
     oder
    -0.90
     alebo
    -0.87
     nebo
    -0.85
     hoặc
    -0.85
     یا
    -0.84
    POSITIVE LOGITS
     Monfieur
    1.09
     myſelf
    1.00
     auffi
    0.99
     ſind
    0.98
     Jefus
    0.98
     ―――――
    0.96
     ſtate
    0.94
     ſmall
    0.94
     ſeveral
    0.94
     Efq
    0.94
    Activations Density 0.159%

    No Known Activations