© 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. 43536
    Prev
    Next
    INDEX
    Explanations

    scientific/political concepts, effects

    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
     myſelf
    -1.22
     Efq
    -1.12
    ſelf
    -1.11
    ſelves
    -1.09
     itſelf
    -1.07
     Theſe
    -1.03
     Majefty
    -1.01
     Monfieur
    -1.01
     themſelves
    -1.00
     leaſt
    -0.96
    POSITIVE LOGITS
    '
    0.68
    .
    0.62
    ’
    0.56
     (
    0.54
    ,
    0.53
    a
    0.52
    (
    0.52
    r
    0.51
    "
    0.49
    i
    0.48
    Activations Density 0.052%

    No Known Activations