© 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. 15731
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    MemoryWarning
    -0.62
    ah
    -0.60
    d
    -0.52
    dars
    -0.51
     d
    -0.50
    quoi
    -0.50
    viewDidLoad
    -0.50
     ah
    -0.50
    dote
    -0.49
    بعاد
    -0.48
    POSITIVE LOGITS
    HtmlAttribute
    0.81
    findpost
    0.65
    RenderAtEndOf
    0.55
    Искәрмәләр
    0.52
    ectady
    0.49
    aure
    0.48
     proprement
    0.47
     yoke
    0.47
     musically
    0.47
    contentLoaded
    0.46
    Activations Density 0.220%

    No Known Activations