© 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. 40763
    Prev
    Next
    INDEX
    Explanations

    Knowing

    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
     Knowing
    -1.37
    Knowing
    -0.92
    verwijspagina
    -0.57
    <bos>
    -0.53
     amnesia
    -0.53
    httphttps
    -0.52
    حوالہ
    -0.52
    IndentedString
    -0.51
    DrawerToggle
    -0.51
    madeus
    -0.50
    POSITIVE LOGITS
    neté
    0.57
    iedy
    0.55
    المشاركات
    0.54
     sinon
    0.53
     Effects
    0.50
    selectAll
    0.50
     Key
    0.49
     widely
    0.49
     Hours
    0.49
     tomorrow
    0.48
    Activations Density 1.101%

    No Known Activations