© 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. 1-CLT-HP
    7. 15699
    Prev
    Next
    INDEX
    Explanations

    classification

    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
     Classi
    -0.54
     Classification
    -0.52
    XtraEditors
    -0.49
     Ru
    -0.48
    orteur
    -0.46
    "{\
    -0.45
    BoxLayout
    -0.43
     مُعرِّف
    -0.43
    HasColumnType
    -0.43
    __':
    -0.41
    POSITIVE LOGITS
    Personensuche
    0.75
    ConstraintMaker
    0.74
    WriteTagHelper
    0.65
    MessageOf
    0.61
    IsContent
    0.60
    Parcelize
    0.58
     Skys
    0.56
    PerformLayout
    0.56
     fidélité
    0.54
     Uff
    0.54
    Activations Density 0.008%

    No Known Activations