© 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. 76073
    Prev
    Next
    INDEX
    Explanations

    News headlines/titles

    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
    tvguidetime
    -1.03
    Personensuche
    -1.00
     ***!
    -0.94
     protoimpl
    -0.91
     EconPapers
    -0.91
    sizeCache
    -0.90
     виправивши
    -0.88
    IsContent
    -0.88
    تقاوى
    -0.86
     betweenstory
    -0.84
    POSITIVE LOGITS
     fore
    0.49
     court
    0.43
     corte
    0.40
     close
    0.37
    里的
    0.36
     covered
    0.35
     διά
    0.35
    newswire
    0.35
     Y
    0.35
     me
    0.35
    Activations Density 0.001%

    No Known Activations