© 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. 4-CLT-HP
    4. 2596
    Prev
    Next
    INDEX
    Explanations

    of

    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
    
    -0.66
    DockStyle
    -0.60
    енча
    -0.51
     protoimpl
    -0.51
    PathVariable
    -0.48
    AnchorStyles
    -0.47
     poppies
    -0.47
    PRNewswire
    -0.46
     collectons
    -0.46
    TableBody
    -0.45
    POSITIVE LOGITS
     ilmo
    0.57
    Referanser
    0.55
    嬸
    0.54
    EditorBrowsable
    0.54
    脚注の使い方
    0.53
     Considerations
    0.53
    ibrill
    0.53
    guém
    0.53
    øl
    0.51
    cznym
    0.50
    Activations Density 0.001%

    No Known Activations