© 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. 45593
    Prev
    Next
    INDEX
    Explanations

    hydraulic

    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
    Immediately
    -0.73
     inmediatamente
    -0.73
     immédiatement
    -0.73
     Immediately
    -0.72
     immediately
    -0.71
    immediately
    -0.65
     chamber
    -0.64
     chambers
    -0.63
     חיצוניים
    -0.63
     immediatamente
    -0.62
    POSITIVE LOGITS
     Metcalf
    0.56
    ίων
    0.54
    numerusform
    0.54
     flagged
    0.50
    깥
    0.50
     handleMessage
    0.49
    ngdoc
    0.48
    iki
    0.48
     perdu
    0.48
     Ordovician
    0.48
    Activations Density 0.065%

    No Known Activations