© 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. 20-CLT-HP
    7. 72424
    Prev
    Next
    INDEX
    Explanations

    academic writing

    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
    出版年
    -0.88
     تضيفلها
    -0.85
    enderror
    -0.81
    contentLoaded
    -0.72
     propOrder
    -0.72
     nakalista
    -0.71
    httphttps
    -0.71
     onCreateView
    -0.70
    ंदीखरीदारी
    -0.69
     surla
    -0.67
    POSITIVE LOGITS
     goal
    0.44
     plastic
    0.44
     emerg
    0.42
     open
    0.42
     situated
    0.41
    Ont
    0.40
     historically
    0.39
     Emer
    0.39
    illen
    0.39
    ilai
    0.38
    Activations Density 0.001%

    No Known Activations