© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 77478
    Prev
    Next
    INDEX
    Explanations

    Foreign Language

    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
    ]<<"
    -0.59
    xhttp
    -0.57
    ]<<
    -0.57
     Sait
    -0.51
    ()];
    -0.51
     dbo
    -0.50
    aints
    -0.49
     BoxFit
    -0.49
    ضايا
    -0.48
    iedler
    -0.48
    POSITIVE LOGITS
    يكب
    0.61
     saites
    0.59
    ագրություններ
    0.59
     Artículo
    0.58
     Article
    0.56
    Article
    0.56
     ARTICLE
    0.53
    HasIndex
    0.52
     يتيمه
    0.52
     createSprite
    0.51
    Activations Density 0.001%

    No Known Activations