© 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. 94825
    Prev
    Next
    INDEX
    Explanations

    modern

    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
    겪
    -0.56
     //$
    -0.47
    revalidate
    -0.47
     For
    -0.47
     Preisen
    -0.47
    zhen
    -0.46
    
    -0.46
     råd
    -0.45
     старости
    -0.45
    rawd
    -0.45
    POSITIVE LOGITS
    AddWithValue
    0.67
     betweenstory
    0.63
    extAlignment
    0.54
     >=",
    0.53
    stuffs
    0.50
    StrictEqual
    0.49
    execSQL
    0.48
     carburetor
    0.48
    InjectAttribute
    0.47
    charpe
    0.47
    Activations Density 0.001%

    No Known Activations