© 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. 5-CLT-HP
    7. 91486
    Prev
    Next
    INDEX
    Explanations

    Code and general internet chatter

    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
    ρίς
    -0.53
     لينك
    -0.51
     betweenstory
    -0.48
    Diwedd
    -0.44
     initComponents
    -0.43
     mijne
    -0.42
    AspNetCore
    -0.42
    ainville
    -0.41
    foglio
    -0.40
    wieś
    -0.40
    POSITIVE LOGITS
    例句
    0.62
     opérés
    0.60
    Kanpo
    0.59
    Externé
    0.58
    chyma
    0.56
     nakalista
    0.56
     فريبيس
    0.55
    новниш
    0.55
     BoxDecoration
    0.55
     JAXBElement
    0.54
    Activations Density 0.001%

    No Known Activations