© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4650
    Prev
    Next
    INDEX
    Explanations

    el

    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
    adpleegd
    -0.80
     صوتيه
    -0.71
    InjectAttribute
    -0.67
     InputDecoration
    -0.65
     estimés
    -0.65
     viewDidLoad
    -0.58
     intptr
    -0.56
     propOrder
    -0.55
    resaid
    -0.54
    djangoproject
    -0.54
    POSITIVE LOGITS
    chen
    0.52
    -
    0.48
    [toxicity=0]
    0.46
     stieg
    0.44
    良好
    0.44
    reg
    0.43
     būtų
    0.42
    <0xBB>
    0.42
     görmek
    0.42
     régionales
    0.41
    Activations Density 0.001%

    No Known Activations