© 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. 5-CLT-HP
    7. 94773
    Prev
    Next
    INDEX
    Explanations

    biological

    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
     étoit
    -0.56
     Grecs
    -0.56
     œufs
    -0.56
     silenzio
    -0.54
     vété
    -0.53
     cavalli
    -0.52
     deberes
    -0.50
     avoient
    -0.50
     réjou
    -0.50
     jueces
    -0.50
    POSITIVE LOGITS
     الحره
    0.65
     AssemblyCulture
    0.64
     GenerationType
    0.63
    msgTypes
    0.63
     tissues
    0.60
    Portale
    0.56
     molecules
    0.56
     cells
    0.54
     structure
    0.53
    utilisons
    0.52
    Activations Density 0.003%

    No Known Activations