© 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. 77378
    Prev
    Next
    INDEX
    Explanations

    play

    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
     kasarigan
    -0.71
    Hentet
    -0.67
     հղումներ
    -0.57
     للمعارف
    -0.57
    iastes
    -0.55
    Personendaten
    -0.55
    脚注の使い方
    -0.55
    ValueGeneration
    -0.53
     ioutil
    -0.53
     juc
    -0.52
    POSITIVE LOGITS
     out
    0.85
     up
    0.68
     to
    0.56
     fast
    0.56
     straight
    0.54
    baik
    0.52
     indios
    0.51
    partes
    0.51
     it
    0.51
     the
    0.49
    Activations Density 0.003%

    No Known Activations