© 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. 0-CLT-HP
    7. 43145
    Prev
    Next
    INDEX
    Explanations

    developing

    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
    ագրություններ
    -0.65
    setof
    -0.62
    eleste
    -0.62
     betweenstory
    -0.60
     createState
    -0.58
     resourceCulture
    -0.58
    /**
    -0.57
    
    -0.56
    MigrationBuilder
    -0.55
    Filmografia
    -0.54
    POSITIVE LOGITS
     lccn
    0.54
     papilla
    0.54
     birth
    0.49
     amphibians
    0.48
     neurons
    0.47
     femur
    0.46
    scriptcase
    0.46
     pancre
    0.45
     pyruvate
    0.45
     humer
    0.45
    Activations Density 0.928%

    No Known Activations