© 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. 14565
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
     GENERATED
    -0.77
     Mende
    -0.54
    RectangleBorder
    -0.52
    posed
    -0.50
    __).
    -0.50
     tabak
    -0.50
     חיצוניים
    -0.49
    SuppressLint
    -0.49
    fromCharCode
    -0.48
    setDo
    -0.47
    POSITIVE LOGITS
     propOrder
    0.59
    исленность
    0.59
    astify
    0.58
    addCriterion
    0.57
     ES
    0.54
    reportWebVitals
    0.53
    AddHtmlAttribute
    0.49
    цездатний
    0.49
    APIView
    0.49
    ObjectContext
    0.48
    Activations Density 0.036%

    No Known Activations