© 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. 5-CLT-HP
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    Freedom of speech/religion

    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
    \{\\
    -0.54
     CURIAM
    -0.50
    Notae
    -0.49
    참고
    -0.49
     initialState
    -0.47
    帖最后由
    -0.47
    BoxShadow
    -0.45
    panjang
    -0.45
    始
    -0.44
    ầy
    -0.44
    POSITIVE LOGITS
    AnchorTagHelper
    0.53
     WaitForSeconds
    0.52
     Pologne
    0.50
    الإنجليزية
    0.50
    kheim
    0.49
     AssemblyCompany
    0.49
     lenker
    0.48
     MainAxisSize
    0.48
    chappe
    0.48
    enschappelijke
    0.47
    Activations Density 0.007%

    No Known Activations