© 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. 4652
    Prev
    Next
    INDEX
    Explanations

    horse

    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
     humaines
    -0.53
     المعيارى
    -0.52
     définiti
    -0.52
    antaranya
    -0.52
     générations
    -0.51
     سكانية
    -0.51
     fermés
    -0.50
     traités
    -0.49
     enfans
    -0.49
     peines
    -0.49
    POSITIVE LOGITS
    featureID
    0.86
    ⓧ
    0.63
    rinfo
    0.60
    IUrlHelper
    0.58
    
    0.57
    RuleContext
    0.57
     للاسماء
    0.57
    لينكات
    0.57
    Hozzáférés
    0.56
    bellar
    0.56
    Activations Density 0.001%

    No Known Activations