© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    Starting or doing something

    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
    igshid
    -0.65
     argint
    -0.61
     sfera
    -0.56
     inicios
    -0.54
     aborto
    -0.53
     intérêt
    -0.53
     esfera
    -0.52
    nictví
    -0.52
     résine
    -0.52
     feroit
    -0.51
    POSITIVE LOGITS
     garg
    0.64
     nakalista
    0.63
     gigantic
    0.54
     something
    0.54
    CloseOperation
    0.53
     remodeling
    0.52
     colossal
    0.52
     rebuilding
    0.52
     betweenstory
    0.51
     recon
    0.50
    Activations Density 0.006%

    No Known Activations