© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    duplicates or parallels

    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
     outputs
    -0.69
     designations
    -0.63
     convictions
    -0.62
     pattern
    -0.60
     feats
    -0.60
     thresholds
    -0.60
    ials
    -0.60
     principles
    -0.59
    initComponents
    -0.59
     intensities
    -0.58
    POSITIVE LOGITS
    #+#
    0.72
    
    0.59
    EndGlobalSection
    0.56
    بوابة
    0.54
    Personensuche
    0.52
    ReusableCell
    0.52
    contentLoaded
    0.51
     typelib
    0.51
    gettyimages
    0.51
     and
    0.51
    Activations Density 0.003%

    No Known Activations