© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90927
    Prev
    Next
    INDEX
    Explanations

    Names and news snippets

    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
    Negative Logits
    ----</
    -0.52
    awaiter
    -0.49
    webElementXpaths
    -0.49
    interopRequire
    -0.49
     Signalez
    -0.49
    heim
    -0.48
    Rüyada
    -0.48
    env
    -0.47
     pé
    -0.46
    Dou
    -0.45
    POSITIVE LOGITS
     Efq
    0.70
    orianCalendar
    0.63
    ]--;
    0.63
    Приятного
    0.63
    !」
    0.62
     auffi
    0.60
     ―――――
    0.60
     Partagez
    0.58
     Houſe
    0.58
     Comédie
    0.58
    Activations Density 0.014%

    No Known Activations