© 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. 5-CLT-HP
    7. 4856
    Prev
    Next
    INDEX
    Explanations

    emissions

    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
    ValueGenerated
    -0.52
     distanciation
    -0.50
     ویکی‌پدی
    -0.50
     '\\;'
    -0.50
    isar
    -0.50
    TacToe
    -0.50
    estacks
    -0.50
    AsUp
    -0.48
    liferay
    -0.48
    AutoScaleMode
    -0.47
    POSITIVE LOGITS
     to
    0.65
     الحره
    0.61
    enumi
    0.56
     Legisl
    0.56
    ("]");
    0.53
    DECLARE
    0.51
     of
    0.51
     sources
    0.47
     Footprint
    0.47
     Assessment
    0.47
    Activations Density 0.001%

    No Known Activations