© 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. 73453
    Prev
    Next
    INDEX
    Explanations

    random data

    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
    vejte
    -0.38
     referência
    -0.38
    __).
    -0.36
     Téléchargez
    -0.35
     leta
    -0.35
     lapangan
    -0.34
     refiere
    -0.34
     ciel
    -0.34
     nakalista
    -0.34
     monnaie
    -0.34
    POSITIVE LOGITS
    AutoScaleMode
    0.74
    HtmlAttribute
    0.73
    ंदीखरीदारी
    0.70
     '{@
    0.70
    AsUp
    0.68
     Schrödinger
    0.67
     snippetHide
    0.66
     EDF
    0.66
     Rada
    0.66
    ClientSize
    0.66
    Activations Density 0.006%

    No Known Activations