© 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. 1-CLT-HP
    7. 10003
    Prev
    Next
    INDEX
    Explanations

    I

    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
     actuels
    -0.58
     ögon
    -0.57
     chimiques
    -0.56
     varandra
    -0.55
     ägg
    -0.54
     hår
    -0.54
     növény
    -0.52
     frukt
    -0.52
     actuelles
    -0.52
     portata
    -0.52
    POSITIVE LOGITS
     berlin
    0.52
     unknownFields
    0.49
     bord
    0.48
    :✨
    0.48
     creek
    0.46
     dept
    0.46
     Савезне
    0.45
    __(/*!
    0.45
    ตัวเอง
    0.45
     river
    0.44
    Activations Density 0.046%

    No Known Activations