© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71343
    Prev
    Next
    INDEX
    Explanations

    Code and records

    np_max-act-logits · 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
    Negative Logits
     MERCHANTABILITY
    -0.49
     contextLoads
    -0.49
    dut
    -0.48
     تعدى
    -0.48
     épaules
    -0.48
    WriteBarrier
    -0.46
     vodi
    -0.45
     Biologie
    -0.44
     lenker
    -0.44
    Viitteet
    -0.43
    POSITIVE LOGITS
    lgari
    0.65
    AndEndTag
    0.56
    LookAnd
    0.55
    addTab
    0.55
     Swarm
    0.53
    modelos
    0.53
    ]--;
    0.52
    =?";
    0.52
    ыгана
    0.52
    ulose
    0.50
    Activations Density 0.003%

    No Known Activations