© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 474
    Prev
    Next
    INDEX
    Explanations

    legal/formal settings

    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
     Италијани
    -0.73
     resourceCulture
    -0.68
    SourceChecksum
    -0.65
    <bos>
    -0.61
    TagMode
    -0.57
     Italijanski
    -0.55
    RegressionTest
    -0.54
    Vidite
    -0.54
    ünst
    -0.52
    astéro
    -0.51
    POSITIVE LOGITS
    Hozzáférés
    0.61
     noastre
    0.52
     BoxDecoration
    0.49
    abinieri
    0.48
    igenschaften
    0.47
    ikä
    0.47
    insegna
    0.47
     گوید
    0.47
    LLocation
    0.47
    umque
    0.47
    Activations Density 0.003%

    No Known Activations