© 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. 4-CLT-HP
    4. 3231
    Prev
    Next
    INDEX
    Explanations

    Random text 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
     CURIAM
    -0.60
    unten
    -0.59
    بوابة
    -0.58
    sizeCache
    -0.56
    urlpatterns
    -0.56
    WriteLiteral
    -0.53
    parms
    -0.52
    GenerationType
    -0.50
    meria
    -0.47
    SequentialGroup
    -0.47
    POSITIVE LOGITS
     Bioaccumulative
    0.57
    grà
    0.54
    ección
    0.52
     BoxFit
    0.51
     ujednoznacz
    0.51
     Copying
    0.50
     complètes
    0.50
     engraçadas
    0.50
     précé
    0.48
     démocr
    0.48
    Activations Density 0.000%

    No Known Activations