© 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. 42893
    Prev
    Next
    INDEX
    Explanations

    energy/engineering

    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
    Билгалдахарш
    -0.86
    ener
    -0.83
    verwijspagina
    -0.71
     basins
    -0.69
    Tembelea
    -0.67
     provinces
    -0.65
     basin
    -0.65
     nakalista
    -0.63
     kaarangay
    -0.63
    StoryboardSegue
    -0.63
    POSITIVE LOGITS
    τία
    0.53
    oara
    0.51
    üedad
    0.50
    a
    0.50
     onStop
    0.48
     TextAppearance
    0.48
     Interessen
    0.48
    e
    0.48
    AsStream
    0.47
    endregion
    0.46
    Activations Density 0.373%

    No Known Activations