© 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. 1377
    Prev
    Next
    INDEX
    Explanations

    India/Middle East

    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
     "
    -0.73
    pa
    -0.65
     '
    -0.63
    pi
    -0.63
     “
    -0.60
    fo
    -0.59
     «
    -0.58
    bi
    -0.56
     su
    -0.56
     ju
    -0.56
    POSITIVE LOGITS
     myſelf
    1.49
     itſelf
    1.38
     Monfieur
    1.38
     himſelf
    1.27
     themſelves
    1.23
     purpoſe
    1.20
     raiſ
    1.19
     pleaſure
    1.16
     ſeveral
    1.15
     houſe
    1.13
    Activations Density 0.114%

    No Known Activations