© 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. 5-CLT-HP
    7. 6203
    Prev
    Next
    INDEX
    Explanations

    "if not" comparisons

    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
    Negative Logits
     sarili
    -0.58
     الدولى
    -0.54
     فقد
    -0.48
    Otherwise
    -0.47
     Otherwise
    -0.46
    的话
    -0.45
    anskje
    -0.44
    {/
    -0.44
    的話
    -0.44
    Anyways
    -0.43
    POSITIVE LOGITS
    Vidite
    0.76
    SourceChecksum
    0.75
    GraphicsUnit
    0.75
    awtextra
    0.69
    OCCURRED
    0.69
     noqa
    0.68
     invece
    0.66
     Waray
    0.63
    ngdoc
    0.62
     ligiloj
    0.61
    Activations Density 0.051%

    No Known Activations