© 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. 1-CLT-HP
    7. 15582
    Prev
    Next
    INDEX
    Explanations

    line

    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
     otomatig
    -0.76
     estimés
    -0.75
    tagHelperRunner
    -0.70
    PYX
    -0.68
    oredCriteria
    -0.68
    webElementGuid
    -0.67
     ddelweddau
    -0.65
     مشين
    -0.64
    WithIOException
    -0.61
     bağlantılar
    -0.59
    POSITIVE LOGITS
    yarnpkg
    0.44
    ofold
    0.44
    Solids
    0.43
     υπό
    0.43
     Driving
    0.42
    Giới
    0.42
    чнее
    0.42
    equalTo
    0.42
     wire
    0.41
    */),
    0.40
    Activations Density 0.002%

    No Known Activations