© 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. 71703
    Prev
    Next
    INDEX
    Explanations

    Academic texts

    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
     않는
    -0.53
     num
    -0.53
     conf
    -0.51
    懒
    -0.47
     ni
    -0.46
    ResourceManager
    -0.46
    NameInMap
    -0.45
     Lac
    -0.45
    Palmarès
    -0.44
     Num
    -0.43
    POSITIVE LOGITS
     pitié
    0.70
     internationaux
    0.68
     femininas
    0.66
     Normdatei
    0.65
    rawDesc
    0.62
     photolibrary
    0.60
     industriels
    0.60
     contextLoads
    0.59
     pluie
    0.59
    seits
    0.58
    Activations Density 0.000%

    No Known Activations