© 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. 76814
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     AssemblyCulture
    -0.52
    imanapun
    -0.50
    parsedMessage
    -0.49
     faculty
    -0.48
     Scaffold
    -0.46
    Tere
    -0.46
    imedia
    -0.45
     pagi
    -0.45
     Jib
    -0.45
    ثيق
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    posedge
    0.62
     snippetHide
    0.60
    GraphicsUnit
    0.57
    GOTREF
    0.57
     урна
    0.56
    ContentAsync
    0.56
    zustellen
    0.52
    Mitglieder
    0.52
    SuccessListener
    0.52
    Activations Density 0.000%

    No Known Activations