© 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. 43514
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     “
    -0.81
    ”
    -0.69
    “
    -0.57
    ’
    -0.53
    .”
    -0.50
     ”
    -0.50
     is
    -0.48
     ‘
    -0.48
     "
    -0.48
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     purpoſe
    1.20
     houſe
    1.18
     myſelf
    1.16
     laſt
    1.13
     itſelf
    1.13
     ſche
    1.09
     ſtate
    1.09
     Anſ
    1.07
     ſch
    1.06
     preſent
    1.06
    Activations Density 0.550%

    No Known Activations