© 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. 0-CLT-HP
    7. 40692
    Prev
    Next
    INDEX
    Explanations

    litis

    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
    adaptiveStyles
    -0.97
     Roskov
    -0.96
    ViewFeatures
    -0.94
    ItemBackground
    -0.90
    UnsafeEnabled
    -0.89
    LayoutStyle
    -0.86
     EconPapers
    -0.84
     masks
    -0.81
    litis
    -0.80
     fallu
    -0.75
    POSITIVE LOGITS
    ing
    0.49
    ↵↵
    0.46
     }^{[
    0.44
     She
    0.43
     He
    0.42
     I
    0.42
     Back
    0.41
     B
    0.40
     Incidentally
    0.40
     Mor
    0.40
    Activations Density 0.620%

    No Known Activations