© 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. 94779
    Prev
    Next
    INDEX
    Explanations

    property

    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
     property
    -1.60
     Property
    -1.48
    property
    -1.46
     properties
    -1.41
     PROPERTY
    -1.38
    Property
    -1.34
     Properties
    -1.29
     propiedades
    -1.27
     proprietà
    -1.22
     propriétés
    -1.22
    POSITIVE LOGITS
     of
    0.56
    e
    0.54
    Mediabestanden
    0.51
     
    0.50
     in
    0.50
     (
    0.50
     escal
    0.49
    ,
    0.47
     also
    0.46
    migrationBuilder
    0.44
    Activations Density 1.571%

    No Known Activations