© 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. 4-CLT-HP
    7. 4802
    Prev
    Next
    INDEX
    Explanations

    to

    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
     ſeveral
    -0.56
     aider
    -0.55
     ſta
    -0.52
     tartalomajánló
    -0.51
    msgTypes
    -0.51
     aids
    -0.50
     kasarigan
    -0.50
     ſur
    -0.49
     ſche
    -0.49
    scalatest
    -0.49
    POSITIVE LOGITS
    ConfigureAwait
    0.64
    GeneratedCode
    0.60
    تفصیلات
    0.58
     utafitiHapana
    0.58
    +#+#
    0.52
    sony
    0.50
     meglio
    0.50
     >=",
    0.50
    ]")]
    0.49
    bien
    0.49
    Activations Density 0.001%

    No Known Activations