© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2368
    Prev
    Next
    INDEX
    Explanations

    Technical documentation and snippets

    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
     שוליים
    -0.82
    Билгалдахарш
    -0.76
    utilisons
    -0.66
    UserScript
    -0.65
     Tense
    -0.61
     >=",
    -0.60
    Искәрмәләр
    -0.60
     Allociné
    -0.60
    elemField
    -0.59
    CppMethod
    -0.59
    POSITIVE LOGITS
     one
    0.54
     return
    0.53
     repeat
    0.52
     case
    0.51
    sing
    0.48
     Deutschlands
    0.48
    epar
    0.48
     they
    0.47
    MENAFN
    0.47
    áról
    0.46
    Activations Density 0.000%

    No Known Activations