© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    ho ger

    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
     ho
    -1.24
     Ho
    -1.05
    Ho
    -0.91
    ho
    -0.87
     program
    -0.62
    ResumeLayout
    -0.59
    rix
    -0.57
     ger
    -0.57
    complexContent
    -0.56
     positive
    -0.55
    POSITIVE LOGITS
     avoient
    0.80
     feroit
    0.78
     étoient
    0.73
     coû
    0.71
     pouvoit
    0.69
     mauva
    0.69
     épar
    0.68
     culturelles
    0.68
     religieuses
    0.67
     ainfi
    0.67
    Activations Density 0.047%

    No Known Activations