© 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. 0-CLT-HP
    4. 1351
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    avelin
    -0.77
     Bethlehem
    -0.66
    ipal
    -0.54
    jago
    -0.51
     urbanos
    -0.51
    AndEndTag
    -0.50
     privées
    -0.50
     initComponents
    -0.50
    nonatomic
    -0.50
     suivantes
    -0.50
    POSITIVE LOGITS
    حوالہ
    0.57
    dersfield
    0.54
    unos
    0.51
     continúas
    0.50
    acherous
    0.50
     invokingState
    0.49
    openzeppelin
    0.49
    pexpr
    0.49
     Specs
    0.49
    reditation
    0.49
    Activations Density 0.204%

    No Known Activations