© 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. 5-CLT-HP
    7. 97950
    Prev
    Next
    INDEX
    Explanations

    theft

    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
     ujednoznacz
    -0.61
     nahilalakip
    -0.61
     Roskov
    -0.60
    Referències
    -0.57
     tartalomajánló
    -0.56
     larceny
    -0.56
     lenker
    -0.55
     conhe
    -0.55
     faim
    -0.54
    Theft
    -0.54
    POSITIVE LOGITS
     GenerationType
    0.63
     doInBackground
    0.62
    openConnection
    0.60
    LoadScene
    0.58
     churches
    0.57
    — 
    0.56
    ControllerAdvice
    0.50
     museums
    0.49
    </thead>
    0.49
    Ecotoxicity
    0.49
    Activations Density 0.002%

    No Known Activations