© 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. 20-CLT-HP
    7. 77567
    Prev
    Next
    INDEX
    Explanations

    Scientific/Biological descriptions

    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
     transfieras
    -0.69
     بيها
    -0.69
     initComponents
    -0.65
     EconPapers
    -0.65
     doInBackground
    -0.64
     initWithFrame
    -0.63
     BoxFit
    -0.63
    WriteTagHelper
    -0.62
    Попис
    -0.59
     desertcart
    -0.58
    POSITIVE LOGITS
     dem
    0.54
     flat
    0.46
     pā
    0.46
    mover
    0.46
    fjspx
    0.45
    flat
    0.44
     dab
    0.43
     sp
    0.43
    Raja
    0.43
     video
    0.42
    Activations Density 0.004%

    No Known Activations