© 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. 20-CLT-HP
    7. 76637
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
     незавершена
    -0.68
     cref
    -0.60
    enderror
    -0.59
     coffees
    -0.59
     rubber
    -0.59
     wig
    -0.54
     تضيفلها
    -0.53
    󠁴
    -0.53
     kett
    -0.53
     incu
    -0.52
    POSITIVE LOGITS
     menengah
    0.56
     ioutil
    0.56
     jsPsych
    0.55
     sèche
    0.53
     camadas
    0.48
     FetchType
    0.47
     kasarigan
    0.46
     camada
    0.46
     colori
    0.45
     smaak
    0.45
    Activations Density 0.000%

    No Known Activations