© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76196
    Prev
    Next
    INDEX
    Explanations

    ran

    np_max-act-logits · 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
     threatened
    -0.58
    umán
    -0.53
     species
    -0.52
     touch
    -0.52
    +</
    -0.50
     domesticated
    -0.49
     invasive
    -0.49
     genome
    -0.49
    kháu
    -0.48
     suscepti
    -0.48
    POSITIVE LOGITS
    webElementXpaths
    0.65
     Normdatei
    0.61
    aarrggbb
    0.60
    GeneratedCode
    0.59
    StoryboardSegue
    0.57
    Diwedd
    0.53
    
    0.53
    DockStyle
    0.53
    
    0.53
    WebVitals
    0.52
    Activations Density 0.000%

    No Known Activations