© 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. 0-CLT-HP
    7. 94054
    Prev
    Next
    INDEX
    Explanations

    nings

    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
    tvguidetime
    -0.69
     للمعارف
    -0.69
    |}{$
    -0.67
    potranspiration
    -0.65
     ModelExpression
    -0.57
    saraba
    -0.56
    AsUp
    -0.56
    ERS
    -0.55
    TagMode
    -0.54
     otomatig
    -0.52
    POSITIVE LOGITS
    EObject
    0.60
     resourceCulture
    0.52
     Ure
    0.51
    ImageContext
    0.51
     دریافت‌شده
    0.50
     teint
    0.50
    Ges
    0.49
     sucedido
    0.49
    stdafx
    0.48
    LST
    0.48
    Activations Density 0.183%

    No Known Activations