© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1678
    Prev
    Next
    INDEX
    Explanations

    place/location

    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
     فريبيس
    -0.76
    principalTable
    -0.70
    DeleteBehavior
    -0.66
     BorderSide
    -0.63
     tartalomajánló
    -0.63
    ernalia
    -0.60
    Rüyada
    -0.60
     ivelany
    -0.59
    InputTagHelper
    -0.59
    AndroidJUnit
    -0.58
    POSITIVE LOGITS
     long
    0.60
    ynb
    0.55
     technical
    0.55
     tri
    0.54
     so
    0.54
     adoption
    0.52
     striking
    0.52
     longstanding
    0.50
     loving
    0.49
     amazing
    0.48
    Activations Density 0.009%

    No Known Activations