© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    gab

    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
     Bate
    -0.54
    enuta
    -0.54
     nakalista
    -0.52
     fermés
    -0.50
    imensional
    -0.47
    neider
    -0.47
    espère
    -0.45
     متعلقه
    -0.45
    door
    -0.45
    th
    -0.45
    POSITIVE LOGITS
     Roskov
    0.62
     EconPapers
    0.58
    +:+
    0.57
    ismet
    0.57
    ContentLoaded
    0.54
     समीक्षक
    0.51
    ביוגרפיה
    0.51
     propOrder
    0.50
    photobucket
    0.50
    ValueStyle
    0.49
    Activations Density 0.003%

    No Known Activations