© 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. 0-CLT-HP
    7. 93187
    Prev
    Next
    INDEX
    Explanations

    anatomical structures

    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
    wares
    -0.51
    setAccessible
    -0.49
     up
    -0.48
    ous
    -0.47
     fu
    -0.47
    AIRE
    -0.46
    ày
    -0.46
     comparative
    -0.46
     bers
    -0.45
     rou
    -0.45
    POSITIVE LOGITS
    发表于
    0.71
     يتيمه
    0.71
     ddelweddau
    0.69
    MemoryWarning
    0.66
     Paglinawan
    0.66
    featureID
    0.65
    UnsafeEnabled
    0.65
     enfans
    0.64
    RegistryLite
    0.64
    Personendaten
    0.63
    Activations Density 0.512%

    No Known Activations