© 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. 43293
    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
     preserved
    -0.87
     Shaped
    -0.75
     shaped
    -0.74
    preserved
    -0.73
     religieuses
    -0.73
    Shaped
    -0.73
    shaped
    -0.72
     recorded
    -0.69
     préserver
    -0.64
     preserving
    -0.64
    POSITIVE LOGITS
    MockMvc
    0.61
    TagHelper
    0.58
    enumi
    0.57
     فريبيس
    0.57
    providedIn
    0.56
    BeginInit
    0.55
    makeText
    0.55
    astify
    0.55
    hyrchwyd
    0.54
    ScopeManager
    0.52
    Activations Density 0.097%

    No Known Activations