© 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. 20-CLT-HP
    7. 72279
    Prev
    Next
    INDEX
    Explanations

    ylus

    np_max-act-logits · 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
    躇
    -0.56
    bootstrapcdn
    -0.55
     محفوظة
    -0.52
     Soil
    -0.51
     <<<<<<<<<<<<<<
    -0.49
    })$}
    -0.49
    __*/
    -0.49
    AlterField
    -0.48
    mondo
    -0.48
     kasarigan
    -0.47
    POSITIVE LOGITS
    ParallelGroup
    0.67
     MainAxisSize
    0.60
    Kaieteur
    0.54
     tomber
    0.52
    ToTable
    0.48
     maroca
    0.47
     Arad
    0.47
    lerc
    0.45
    ICOLON
    0.45
     RouterModule
    0.45
    Activations Density 0.006%

    No Known Activations