© 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. 4-CLT-HP
    7. 2771
    Prev
    Next
    INDEX
    Explanations

    Agents and representation

    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
    XmlAccessorType
    -0.52
     الرياضيه
    -0.52
    endmodule
    -0.51
     bezeichneter
    -0.51
    存于互联网档案馆
    -0.50
    ciaż
    -0.49
    IntoConstraints
    -0.49
    outState
    -0.47
    Хьажоргаш
    -0.47
     SqlCommand
    -0.47
    POSITIVE LOGITS
     provoc
    0.71
     of
    0.62
     Nieto
    0.54
    clusal
    0.54
     jsPsych
    0.53
    ngua
    0.53
    teatro
    0.52
     COMPET
    0.52
     lenker
    0.51
     ivelany
    0.51
    Activations Density 0.002%

    No Known Activations