© 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. 96717
    Prev
    Next
    INDEX
    Explanations

    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
    kháu
    -0.64
     clinic
    -0.54
     medical
    -0.54
    MethodManager
    -0.53
     cures
    -0.52
     clinical
    -0.50
    minecraftforge
    -0.50
    MLLoader
    -0.50
    elsif
    -0.48
     treatment
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.76
    Portail
    0.73
    Datuak
    0.57
     CreateTagHelper
    0.56
    Carriera
    0.54
    stdc
    0.52
     Depression
    0.52
    허
    0.50
     weißem
    0.49
    Notae
    0.49
    Activations Density 0.000%

    No Known Activations