© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75154
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    corp
    -0.51
    세
    -0.50
    jooq
    -0.49
    Sunlight
    -0.49
    PerformLayout
    -0.49
    ๆ
    -0.48
     Cro
    -0.47
     (!__
    -0.47
     Alive
    -0.47
     bande
    -0.47
    POSITIVE LOGITS
     Walkover
    0.65
    ItemLayout
    0.54
    seamnă
    0.51
     Exactos
    0.50
    wts
    0.50
    )"),
    0.50
     дописавши
    0.50
     färg
    0.49
     EconPapers
    0.49
    WTS
    0.48
    Activations Density 0.001%

    No Known Activations