© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92737
    Prev
    Next
    INDEX
    Explanations

    relative measurements

    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
     cytoplasmic
    -0.63
     medulla
    -0.63
     ferdig
    -0.59
    contentLoaded
    -0.55
     Sociales
    -0.54
     igneous
    -0.52
     diaphragm
    -0.52
    itinéraire
    -0.52
    instan
    -0.51
     pituitary
    -0.51
    POSITIVE LOGITS
    RTEX
    0.60
     AssemblyTitle
    0.57
     saites
    0.56
    <()>
    0.55
    gages
    0.55
     autorytatywna
    0.54
     INTERESAR
    0.54
    GOTREF
    0.53
     VIDEOTAPE
    0.51
    eriks
    0.50
    Activations Density 0.091%

    No Known Activations