© 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. 4378
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     strtok
    -0.59
    mtable
    -0.59
    reactstrap
    -0.57
    MENAFN
    -0.55
    IVEREF
    -0.50
     Geraadpleegd
    -0.49
    degna
    -0.49
    ąż
    -0.49
    WebControls
    -0.48
    ностран
    -0.47
    POSITIVE LOGITS
    发表于
    0.61
    はじめに
    0.60
    CodeAttribute
    0.57
     gawas
    0.48
    preco
    0.47
     psycopg
    0.46
    saraba
    0.46
    getSupport
    0.46
     imperio
    0.45
     kasarigan
    0.45
    Activations Density 0.003%

    No Known Activations