© 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. 75587
    Prev
    Next
    INDEX
    Explanations

    have

    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
     growth
    -0.52
     McIn
    -0.49
     growths
    -0.46
    InjectMocks
    -0.46
    Pranala
    -0.44
     efforts
    -0.44
     development
    -0.44
     progress
    -0.42
     Fortsch
    -0.42
    setGeometry
    -0.42
    POSITIVE LOGITS
    IsContent
    0.79
    ArrowToggle
    0.77
    AsUp
    0.77
    AddTagHelper
    0.70
    Race
    0.67
     démocr
    0.67
    Попис
    0.66
     dépens
    0.65
     समीक्षाओं
    0.65
     race
    0.63
    Activations Density 0.000%

    No Known Activations