© 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. 93137
    Prev
    Next
    INDEX
    Explanations

    2

    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
    2
    -0.94
    ↵
    -0.61
     f
    -0.44
    ２
    -0.43
    l
    -0.40
    f
    -0.40
     про
    -0.39
     
    -0.39
    Re
    -0.39
     un
    -0.39
    POSITIVE LOGITS
     myſelf
    1.15
     itſelf
    1.14
     Monfieur
    1.07
     سكانية
    1.06
     ſeveral
    1.05
     himſelf
    1.04
    ReusableCell
    1.03
     iſt
    1.01
     Efq
    1.00
     faſt
    0.97
    Activations Density 0.082%

    No Known Activations