© 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. 20-CLT-HP
    7. 76113
    Prev
    Next
    INDEX
    Explanations

    code imports

    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
     دیکھیے
    -0.72
    IVEREF
    -0.71
    SourceChecksum
    -0.69
    Obrázky
    -0.68
    AndEndTag
    -0.66
    ItemBackground
    -0.65
     Normdatei
    -0.63
    msgTypes
    -0.62
    رشف
    -0.61
     preſent
    -0.60
    POSITIVE LOGITS
     properly
    0.87
    properly
    0.80
     proper
    0.79
     PROPER
    0.70
    proper
    0.69
     round
    0.69
     Proper
    0.69
    Proper
    0.68
     Properly
    0.60
     much
    0.51
    Activations Density 0.001%

    No Known Activations