© 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. 41146
    Prev
    Next
    INDEX
    Explanations

    ethnic groups

    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
    ing
    -0.60
    {}/
    -0.51
    poly
    -0.49
    ển
    -0.48
     Reference
    -0.48
     }],
    -0.48
    es
    -0.48
     Sekund
    -0.47
    Index
    -0.46
     PrintWriter
    -0.46
    POSITIVE LOGITS
    numerusform
    0.67
    جوايز
    0.65
    adona
    0.65
     informée
    0.64
     GetEnumerator
    0.63
    idopsis
    0.61
    complexContent
    0.61
    abrigo
    0.59
    ocities
    0.59
     Bohr
    0.59
    Activations Density 1.035%

    No Known Activations