© 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. 4810
    Prev
    Next
    INDEX
    Explanations

    Hormonal or ":"

    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
     resourceCulture
    -0.73
    دانشنامهٔ
    -0.55
     CreateTagHelper
    -0.55
    脚注の使い方
    -0.53
    хьтан
    -0.52
    ftagPool
    -0.52
    MessageTagHelper
    -0.52
    betic
    -0.50
     transfieras
    -0.48
    hljs
    -0.47
    POSITIVE LOGITS
     uſed
    0.65
     Monfieur
    0.65
     Theſe
    0.60
     Efq
    0.59
     perſon
    0.59
     myſelf
    0.58
    ParallelGroup
    0.57
     ſeveral
    0.57
     uſe
    0.56
    üz
    0.55
    Activations Density 0.000%

    No Known Activations