© 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. 77879
    Prev
    Next
    INDEX
    Explanations

    Technical text/context

    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
     snippetHide
    -0.97
    tanleria
    -0.80
    buttonBar
    -0.77
    ulink
    -0.74
     nakalista
    -0.71
    ThemeOverlay
    -0.71
    tagHelperRunner
    -0.70
    SharedDtor
    -0.69
    Vidite
    -0.69
    IContainer
    -0.68
    POSITIVE LOGITS
     for
    0.46
     Zust
    0.43
    SearchView
    0.43
     to
    0.43
     للاست
    0.42
     mourir
    0.39
     lavoratori
    0.39
     juguete
    0.39
     sacerdotes
    0.39
     simplement
    0.38
    Activations Density 0.001%

    No Known Activations