© 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. 5-CLT-HP
    7. 97371
    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
     مرئيه
    -0.82
     Савезне
    -0.73
     EconPapers
    -0.73
    MethodManager
    -0.72
     disambiguazione
    -0.69
    NameInMap
    -0.68
    ioutil
    -0.66
     Мексичка
    -0.66
    новниш
    -0.65
     propOrder
    -0.65
    POSITIVE LOGITS
    tolsó
    0.46
    AutoScaleMode
    0.37
     Pro
    0.36
     kjent
    0.36
     diario
    0.36
     опыт
    0.36
    pilar
    0.35
    ERD
    0.35
    ="{
    0.34
    trx
    0.34
    Activations Density 0.007%

    No Known Activations