© 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. 4-CLT-HP
    7. 612
    Prev
    Next
    INDEX
    Explanations

    "things are"

    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
    AndEndTag
    -0.65
     pillows
    -0.56
    ']){
    -0.51
     legyen
    -0.50
    "}>
    -0.49
    ">−
    -0.49
     amitié
    -0.48
     fidélité
    -0.47
    gwt
    -0.46
    avimas
    -0.46
    POSITIVE LOGITS
     endfor
    0.63
    IUrlHelper
    0.58
    TintMode
    0.57
     wireType
    0.57
    Autoritní
    0.56
    Alike
    0.54
    adaptiveStyles
    0.54
    pyplot
    0.54
    ListItemIcon
    0.54
    NICE
    0.53
    Activations Density 0.017%

    No Known Activations