© 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. 0-CLT-HP
    7. 40624
    Prev
    Next
    INDEX
    Explanations

    Market/Mark

    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
     Mark
    -0.74
     relative
    -0.52
    Mark
    -0.49
     MARK
    -0.48
     sau
    -0.48
     Santa
    -0.47
     of
    -0.47
     el
    -0.46
     mark
    -0.46
     flex
    -0.45
    POSITIVE LOGITS
     itſelf
    0.96
     ſche
    0.93
     Monfieur
    0.93
     myſelf
    0.92
     purpoſe
    0.92
     ſtate
    0.91
     ſte
    0.90
     Efq
    0.90
     ſever
    0.88
     Reſ
    0.88
    Activations Density 0.130%

    No Known Activations