© 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. 0-CLT-HP
    7. 41683
    Prev
    Next
    INDEX
    Explanations

    industri

    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
     GMAT
    -0.93
    nova
    -0.67
     industri
    -0.64
    BrowserModule
    -0.57
    
    -0.54
     geslacht
    -0.52
    kloped
    -0.52
    __":
    -0.52
     للمعارف
    -0.51
    CppMethod
    -0.50
    POSITIVE LOGITS
    holdet
    0.58
    Allo
    0.56
     voks
    0.56
     poorest
    0.52
     présidenti
    0.52
    føl
    0.52
     gjø
    0.51
    aos
    0.50
     betale
    0.49
    als
    0.49
    Activations Density 0.194%

    No Known Activations