© 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. 1-CLT-HP
    7. 10522
    Prev
    Next
    INDEX
    Explanations

    res

    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
     فريبيس
    -0.59
     vectorielles
    -0.57
     vectorielle
    -0.51
    ErrorListener
    -0.50
    ClientSize
    -0.47
     vettoriale
    -0.47
    UMBIA
    -0.46
    devamını
    -0.44
     démocr
    -0.44
     civile
    -0.44
    POSITIVE LOGITS
     الرياضيه
    0.63
     autorytatywna
    0.58
     Yag
    0.54
    といけない
    0.52
     ▸
    0.52
    帖最后由
    0.51
     />}
    0.50
    Rap
    0.50
    ärä
    0.50
     Pash
    0.50
    Activations Density 0.084%

    No Known Activations