© 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. 98280
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Cæsar
    -0.71
     Majefty
    -0.65
    ſelves
    -0.65
     Diſ
    -0.63
     Shakspeare
    -0.63
     متعلقه
    -0.62
     themſelves
    -0.60
     foon
    -0.60
     rak
    -0.60
     includes
    -0.60
    POSITIVE LOGITS
    ValueGeneration
    0.53
     vérit
    0.51
     ministres
    0.45
     excès
    0.45
     réfugiés
    0.45
     intptr
    0.43
     présidenti
    0.43
    GEBURTS
    0.43
     récentes
    0.43
     témoins
    0.41
    Activations Density 1.439%

    No Known Activations