© 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. 38296
    Prev
    Next
    INDEX
    Explanations

    wet

    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
     wet
    -0.91
     hard
    -0.79
     Wet
    -0.68
    ed
    -0.60
     Hard
    -0.59
     basah
    -0.55
    Hard
    -0.54
    dehydes
    -0.52
     orizz
    -0.52
    Wet
    -0.50
    POSITIVE LOGITS
    +#+#
    0.88
     smtplib
    0.88
    AxisAlignment
    0.81
     defaultstate
    0.81
     Normdatei
    0.74
    StoryboardSegue
    0.74
    
    0.74
    :✨
    0.73
     snippetHide
    0.73
    EndInit
    0.73
    Activations Density 0.269%

    No Known Activations