© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    science and space

    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
     للاسماء
    -0.80
    principalTable
    -0.80
     <=",
    -0.75
     EconPapers
    -0.73
    ///</
    -0.70
    Gambas
    -0.67
    rowave
    -0.67
    findpost
    -0.65
    StoryboardSegue
    -0.64
    Geplaatst
    -0.63
    POSITIVE LOGITS
    igi
    0.45
     rising
    0.45
     transporting
    0.44
     doch
    0.44
     and
    0.42
     Seguridad
    0.41
     card
    0.41
     langer
    0.40
     rich
    0.40
     tertinggi
    0.39
    Activations Density 0.010%

    No Known Activations