© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41510
    Prev
    Next
    INDEX
    Explanations

    ;

    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
     avoient
    -0.75
     aikaa
    -0.71
     étoient
    -0.68
     listos
    -0.66
     militaires
    -0.62
    visející
    -0.62
     vendus
    -0.62
     artesanales
    -0.60
     garanzia
    -0.60
     pubblicità
    -0.60
    POSITIVE LOGITS
    ,
    0.91
     oxidation
    0.62
     intracellular
    0.60
     thermal
    0.60
     chlor
    0.60
     oxidative
    0.59
     hydrolysis
    0.59
     soluble
    0.57
     adrenal
    0.57
     inorganic
    0.57
    Activations Density 0.081%

    No Known Activations