© 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. 5-CLT-HP
    7. 92103
    Prev
    Next
    INDEX
    Explanations

    period

    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
     vermelhas
    -0.86
     preghiera
    -0.85
     trasparente
    -0.83
     tiroirs
    -0.83
     spesa
    -0.80
     feroit
    -0.79
     paesaggio
    -0.78
     profondità
    -0.78
     mourut
    -0.77
     femininas
    -0.76
    POSITIVE LOGITS
     co
    0.55
     cic
    0.50
     cho
    0.48
     oro
    0.47
     pri
    0.44
     als
    0.44
     net
    0.44
     ala
    0.43
     bol
    0.43
     cre
    0.43
    Activations Density 0.002%

    No Known Activations