© 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. 5-CLT-HP
    7. 3813
    Prev
    Next
    INDEX
    Explanations

    Memories

    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
    الحياه
    -0.93
    ImageContext
    -0.87
     FetchType
    -0.85
     AssemblyCulture
    -0.83
    
    -0.82
     defaultstate
    -0.82
    Portály
    -0.81
    fjspx
    -0.81
    gameserver
    -0.80
     مرئيه
    -0.79
    POSITIVE LOGITS
    sius
    0.46
    ständig
    0.41
    Available
    0.37
    .$,
    0.37
    ical
    0.36
    suchen
    0.36
    consulté
    0.35
    sion
    0.35
     yle
    0.35
     either
    0.34
    Activations Density 0.000%

    No Known Activations