© 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. 1-CLT-HP
    7. 46026
    Prev
    Next
    INDEX
    Explanations

    alle

    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
    AnchorStyles
    -0.54
    tade
    -0.48
     Dougherty
    -0.48
    SuppressLint
    -0.47
    iyle
    -0.47
    ornis
    -0.47
     tache
    -0.46
    UnusedPrivate
    -0.46
    ebay
    -0.46
     funktion
    -0.45
    POSITIVE LOGITS
     cérami
    0.59
     saites
    0.57
    contentLoaded
    0.56
     AssemblyCulture
    0.56
    RTEX
    0.55
    dragen
    0.55
    Веду
    0.52
    writeFieldEnd
    0.52
     Paglinawan
    0.51
     الحره
    0.51
    Activations Density 0.036%

    No Known Activations