© 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. 73053
    Prev
    Next
    INDEX
    Explanations

    par

    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
    SpringBootTest
    -0.74
     StyleSheet
    -0.59
     doInBackground
    -0.57
    ThroughAttribute
    -0.57
    Билгалдахарш
    -0.56
     tartalomajánló
    -0.56
     correctes
    -0.56
    (")");
    -0.55
     الرياضيه
    -0.54
    bject
    -0.54
    POSITIVE LOGITS
    motion
    0.56
     Motion
    0.56
     motion
    0.53
    Motion
    0.51
    Filmographie
    0.49
     بتاريخ
    0.48
     eerder
    0.47
     MOTION
    0.47
    acry
    0.46
    존
    0.45
    Activations Density 0.001%

    No Known Activations