© 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. 92628
    Prev
    Next
    INDEX
    Explanations

    Code/text documents

    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
     Flock
    -0.55
     Condu
    -0.53
    ạn
    -0.53
    ANSA
    -0.52
     grade
    -0.52
     branche
    -0.51
     Fick
    -0.50
     grades
    -0.50
    ën
    -0.50
     lī
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.67
    Personendaten
    0.63
    setVerticalGroup
    0.56
     defaultstate
    0.53
    stdc
    0.53
    JHEP
    0.51
     ligiloj
    0.49
     borda
    0.48
    MessageTagHelper
    0.47
    endphp
    0.47
    Activations Density 0.012%

    No Known Activations