© 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. 4889
    Prev
    Next
    INDEX
    Explanations

    coding/markup

    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
    cemia
    -0.47
     beginnetje
    -0.46
     circular
    -0.44
    umba
    -0.43
    oplasmic
    -0.43
    toral
    -0.42
    outons
    -0.41
     TEM
    -0.40
    pola
    -0.40
    omeness
    -0.39
    POSITIVE LOGITS
    PerformLayout
    0.69
    CloseOperation
    0.69
     autorytatywna
    0.62
    Affiliation
    0.60
    ngdoc
    0.59
    EndProject
    0.57
    Americans
    0.57
     RequestMethod
    0.56
     Americans
    0.56
    Indians
    0.56
    Activations Density 0.001%

    No Known Activations