© 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. 0-CLT-HP
    7. 93954
    Prev
    Next
    INDEX
    Explanations

    level

    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
     level
    -1.36
    level
    -1.18
    Level
    -1.10
     Level
    -1.10
     LEVEL
    -1.05
     levels
    -1.00
    LEVEL
    -0.98
     Levels
    -0.94
     nivå
    -0.92
    levels
    -0.90
    POSITIVE LOGITS
     MainAxisSize
    0.86
     propOrder
    0.78
     Chwiliwch
    0.71
    enterOuterAlt
    0.71
    anterie
    0.70
     '\\;'
    0.68
     firebaseConfig
    0.68
    GEBURTSDATUM
    0.67
     CreateTagHelper
    0.65
     nahilalakip
    0.65
    Activations Density 0.133%

    No Known Activations