© 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. 20-CLT-HP
    7. 77727
    Prev
    Next
    INDEX
    Explanations

    Incident, legal, technical texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ViewInit
    -0.48
    TypedDataSet
    -0.46
    Pi
    -0.45
     cref
    -0.42
    Palmarès
    -0.42
     the
    -0.42
    getValueAt
    -0.41
    antz
    -0.41
     Pi
    -0.40
    μο
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.72
    UnsafeEnabled
    0.60
    exitRule
    0.56
     ChromeDriver
    0.56
    HomeAsUp
    0.56
    webElementXpaths
    0.53
     typelib
    0.53
    MARKET
    0.52
    Acab
    0.51
    Nazionale
    0.50
    Activations Density 0.000%

    No Known Activations