© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    quantitatively

    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
    yonel
    -0.59
    lably
    -0.56
    {`
    -0.53
     băr
    -0.53
     magnitudes
    -0.52
     CURIAM
    -0.52
     magnitude
    -0.51
    ỡng
    -0.50
    出版年
    -0.50
     يتيمه
    -0.49
    POSITIVE LOGITS
    arraycopy
    0.59
     CreateTagHelper
    0.57
     correct
    0.57
     giusto
    0.56
     sufficient
    0.54
    GraphicsUnit
    0.53
     good
    0.53
    WireFormatLite
    0.52
    enumi
    0.50
     secure
    0.49
    Activations Density 0.039%

    No Known Activations