© 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. 1-CLT-HP
    7. 12407
    Prev
    Next
    INDEX
    Explanations

    water, of

    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
    DoubleQuotes
    -0.49
     Elek
    -0.46
    ulemon
    -0.44
    }{*}{
    -0.44
    esgue
    -0.43
    AndEndTag
    -0.43
     linkovi
    -0.43
     rueda
    -0.43
    ITO
    -0.43
     ladder
    -0.43
    POSITIVE LOGITS
    principalTable
    0.61
    :+:
    0.55
     bancaire
    0.54
    ειτουργ
    0.54
    原始内容存档
    0.52
     Anggota
    0.52
     économ
    0.52
     Serikat
    0.51
    GEBURTS
    0.51
     nära
    0.51
    Activations Density 0.096%

    No Known Activations