© 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. 4-CLT-HP
    7. 315
    Prev
    Next
    INDEX
    Explanations

    were

    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
    ONCE
    -0.59
     ONCE
    -0.59
    nunca
    -0.52
     היתה
    -0.51
     then
    -0.51
    antaranya
    -0.50
    queles
    -0.50
    once
    -0.49
     NEVER
    -0.48
     damaligen
    -0.48
    POSITIVE LOGITS
    enumi
    0.80
    RectangleBorder
    0.68
     BoxDecoration
    0.67
     /\.
    0.67
     EconPapers
    0.67
     استنادى
    0.64
    </thead>
    0.60
    ]^{-
    0.57
    ++)
    0.57
    BeginInit
    0.56
    Activations Density 0.004%

    No Known Activations