© 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. 0-CLT-HP
    4. 92350
    Prev
    Next
    INDEX
    Explanations

    overall

    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
     overall
    -1.63
    overall
    -1.53
    Overall
    -1.50
     Overall
    -1.48
    er
    -1.02
    Lähteet
    -0.89
     overal
    -0.87
    整體
    -0.85
    OVERALL
    -0.79
    Izvori
    -0.71
    POSITIVE LOGITS
    RegistryLite
    0.85
    npr
    0.53
    tvguidetime
    0.52
    WriteTagHelper
    0.49
    ت
    0.49
     Purpose
    0.49
    OPSIS
    0.48
    fonte
    0.47
     stakeholder
    0.47
     Kamer
    0.47
    Activations Density 0.061%

    No Known Activations