© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93805
    Prev
    Next
    INDEX
    Explanations

    math

    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
    contentLoaded
    -0.53
    sizeCache
    -0.52
     témoins
    -0.52
     Normdatei
    -0.50
    Dtor
    -0.50
    detectChanges
    -0.48
    PreferredItem
    -0.45
     Committee
    -0.45
    تقاوى
    -0.45
    хин
    -0.45
    POSITIVE LOGITS
    ########.
    0.74
    Ữ
    0.52
    INUM
    0.52
    mons
    0.52
     Rambo
    0.51
    KeySpec
    0.50
    ⓧ
    0.50
    Kjelder
    0.50
    complexContent
    0.50
    Jub
    0.50
    Activations Density 0.002%

    No Known Activations