© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    know

    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
    çı
    -0.47
     hablando
    -0.45
     Republics
    -0.43
    votre
    -0.43
     formando
    -0.43
     whereupon
    -0.42
     generando
    -0.41
     republics
    -0.41
     buscando
    -0.41
     procurando
    -0.41
    POSITIVE LOGITS
     nothing
    0.91
     esternos
    0.77
    énario
    0.76
    nothing
    0.71
    الحياه
    0.71
    __':
    0.70
     EconPapers
    0.70
     they
    0.68
    BeginContext
    0.67
    AppMethodBeat
    0.67
    Activations Density 0.004%

    No Known Activations