© 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. 4-CLT-HP
    7. 857
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Arabia
    -0.50
     toen
    -0.49
     ThemeData
    -0.49
    วะ
    -0.49
    ecko
    -0.47
     iprot
    -0.47
    Rihanna
    -0.47
     Contempor
    -0.47
    னர்
    -0.47
    obat
    -0.46
    POSITIVE LOGITS
     makeStyles
    0.64
     kasarigan
    0.58
    بوابة
    0.50
    AddHtmlAttribute
    0.49
    nius
    0.47
    setViewportView
    0.47
    jooq
    0.46
    paign
    0.45
     Chap
    0.45
    ngrx
    0.45
    Activations Density 0.001%

    No Known Activations