© 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. 9650
    Prev
    Next
    INDEX
    Explanations

    names, invoices, types

    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
     Watson
    -1.91
    Watson
    -1.63
     WATSON
    -1.23
     strong
    -0.46
     North
    -0.44
     multi
    -0.40
     clear
    -0.40
    веро
    -0.39
    ẵn
    -0.39
    toupper
    -0.39
    POSITIVE LOGITS
    mtrl
    0.81
    HomeAsUpEnabled
    0.76
     ModelExpression
    0.76
    MLLoader
    0.75
     itſelf
    0.75
    findpost
    0.74
    Хьажоргаш
    0.73
    حوالہ
    0.72
     purpoſe
    0.71
     оригіналу
    0.70
    Activations Density 0.014%

    No Known Activations