© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91896
    Prev
    Next
    INDEX
    Explanations

    routine, typical

    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
     متعلقه
    -0.60
     صوتيه
    -0.52
     autorytatywna
    -0.52
     '\\;'
    -0.50
    Искәрмәләр
    -0.50
    leski
    -0.48
     дописавши
    -0.48
    cookieParser
    -0.45
    říklad
    -0.45
     ["",
    -0.43
    POSITIVE LOGITS
     use
    0.56
    MessageOf
    0.56
    JScrollPane
    0.52
    CppCodeGen
    0.51
    pch
    0.49
    gameserver
    0.48
    idelberg
    0.48
     necessità
    0.47
     мәкал
    0.46
    RefreshLayout
    0.45
    Activations Density 0.001%

    No Known Activations