© 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. 94583
    Prev
    Next
    INDEX
    Explanations

    technical/legal text

    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
    SourceChecksum
    -0.70
    featureID
    -0.60
    ècie
    -0.60
     Efq
    -0.59
     wikipagina
    -0.54
    ValueGeneration
    -0.52
     Anzeigen
    -0.49
     vétérina
    -0.49
     hogs
    -0.49
    +#+#
    -0.48
    POSITIVE LOGITS
     Paglinawan
    0.53
    
    0.52
    __":
    0.51
     anything
    0.50
    __':
    0.50
     JUGA
    0.50
    InSection
    0.49
    "]="
    0.49
     LESS
    0.48
     less
    0.48
    Activations Density 0.012%

    No Known Activations