© 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. 5-CLT-HP
    7. 92511
    Prev
    Next
    INDEX
    Explanations

    ize

    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
    ]-'
    -0.63
    FontOfSize
    -0.61
    NUMX
    -0.60
     inability
    -0.58
     InputDecoration
    -0.56
     BnF
    -0.54
    只好
    -0.54
    bitField
    -0.54
     Possibility
    -0.53
    }`}>
    -0.53
    POSITIVE LOGITS
     iprot
    0.55
     significant
    0.54
    webElementXpaths
    0.52
     extensive
    0.49
     substantial
    0.48
     greater
    0.48
     part
    0.48
     major
    0.48
     others
    0.48
     most
    0.48
    Activations Density 0.025%

    No Known Activations