© 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. 91559
    Prev
    Next
    INDEX
    Explanations

    ual

    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
    ↵
    -0.48
    ↵↵
    -0.39
    port
    -0.36
    立
    -0.36
    men
    -0.33
    uzi
    -0.33
     https
    -0.32
    בע
    -0.32
     muuta
    -0.30
     especializados
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    1.32
    httphttps
    1.31
     nahilalakip
    1.28
    ^(@)
    1.16
    Geplaatst
    1.16
    SharedDtor
    1.13
     مشين
    1.12
     للمعارف
    1.09
    expandindo
    1.09
    InjectAttribute
    1.07
    Activations Density 0.000%

    No Known Activations