© 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. 0-CLT-HP
    7. 94848
    Prev
    Next
    INDEX
    Explanations

    also

    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
    based
    -0.46
     is
    -0.45
     can
    -0.44
     get
    -0.44
    Triple
    -0.42
     hadir
    -0.42
     también
    -0.41
     based
    -0.40
     also
    -0.40
     também
    -0.39
    POSITIVE LOGITS
     propOrder
    1.01
    GEBURTSDATUM
    0.94
     <=",
    0.93
     resourceCulture
    0.91
    Geplaatst
    0.88
    AddHtmlAttribute
    0.88
    featureID
    0.88
    IUrlHelper
    0.88
     CURIAM
    0.87
     NSCoder
    0.87
    Activations Density 0.231%

    No Known Activations