© 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. 97924
    Prev
    Next
    INDEX
    Explanations

    Linq

    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
    +#+#
    -0.84
    CppMethod
    -0.78
    SharedDtor
    -0.77
     ddelweddau
    -0.75
     mergeFrom
    -0.74
    }}]{
    -0.73
    #+#
    -0.72
    "}")
    -0.71
    Diwedd
    -0.71
    ']")
    -0.71
    POSITIVE LOGITS
    Rich
    0.54
    It
    0.54
    This
    0.50
    Made
    0.46
    Set
    0.45
    The
    0.45
    C
    0.44
    Com
    0.44
    Our
    0.44
    Ren
    0.44
    Activations Density 0.001%

    No Known Activations