© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    Code, databases, scientific texts

    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
    WireFormatLite
    -0.56
    HasMaxLength
    -0.55
    OWA
    -0.52
    HtmlAttribute
    -0.49
    owa
    -0.49
    нская
    -0.48
     coreana
    -0.48
    bitat
    -0.48
     aes
    -0.47
    rdida
    -0.47
    POSITIVE LOGITS
     facie
    0.63
    ⓧ
    0.63
     SwitchCompat
    0.56
    
    0.55
    iddhar
    0.53
    AndroidJUnit
    0.53
    WebVitals
    0.53
    igail
    0.53
    URLException
    0.52
     saites
    0.52
    Activations Density 0.010%

    No Known Activations