© 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. 1-CLT-HP
    7. 15536
    Prev
    Next
    INDEX
    Explanations

    Sikh

    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
    UnusedPrivate
    -0.64
    webElementGuid
    -0.63
    AutoScaleMode
    -0.61
    IUrlHelper
    -0.56
     CreateTagHelper
    -0.56
     onCreateView
    -0.54
     Rumuni
    -0.53
     mergeFrom
    -0.53
     kasarigan
    -0.52
    AndroidJUnit
    -0.52
    POSITIVE LOGITS
    se
    0.59
    complexType
    0.55
     déb
    0.52
     sab
    0.52
    seth
    0.48
    bar
    0.47
    j
    0.46
    bieter
    0.46
    pole
    0.46
    mar
    0.46
    Activations Density 0.025%

    No Known Activations