© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14888
    Prev
    Next
    INDEX
    Explanations

    our

    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
     Wikimedijinoj
    -0.63
     Waray
    -0.59
    ientôt
    -0.57
     שוליים
    -0.56
     compositional
    -0.54
    esgue
    -0.54
     Autorizaciones
    -0.54
     gepubliceerd
    -0.53
    DockStyle
    -0.53
    Tikang
    -0.53
    POSITIVE LOGITS
     resourceCulture
    0.69
     насељу
    0.58
     استنادى
    0.57
    multer
    0.53
     wash
    0.47
    wash
    0.47
     couper
    0.45
     unfortunately
    0.45
    tisgarh
    0.45
    FactoryBean
    0.45
    Activations Density 0.002%

    No Known Activations