© 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. 1-CLT-HP
    7. 15780
    Prev
    Next
    INDEX
    Explanations

    results, outcomes, effects

    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
    PMailer
    -0.58
     otomatig
    -0.57
    unts
    -0.54
     beauté
    -0.53
    ्रिया
    -0.52
    र्भ
    -0.52
    ContextHolder
    -0.52
     ModelExpression
    -0.52
    bootstrapcdn
    -0.52
     Dhabi
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.51
     OnInit
    0.51
    ages
    0.48
     arşivlendi
    0.48
     Flin
    0.47
     linen
    0.47
    xFFFFFF
    0.46
    rait
    0.46
    licity
    0.45
    ilitate
    0.45
    Activations Density 0.017%

    No Known Activations