© 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. 40295
    Prev
    Next
    INDEX
    Explanations

    organizations or groups

    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
     ainfi
    -0.87
     feroit
    -0.83
     étoit
    -0.82
     auffi
    -0.82
     auroit
    -0.81
     pouvoit
    -0.79
     myſelf
    -0.78
     Monfieur
    -0.77
    ſelf
    -0.75
     Dukes
    -0.74
    POSITIVE LOGITS
    ViewFeatures
    0.54
     interpret
    0.48
     All
    0.44
    ,
    0.44
    tsch
    0.43
    sos
    0.42
     Data
    0.42
     tem
    0.41
     do
    0.41
     vend
    0.41
    Activations Density 0.100%

    No Known Activations