© 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. 92524
    Prev
    Next
    INDEX
    Explanations

    law

    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
    rungsseite
    -0.67
    irmanship
    -0.47
    saveButton
    -0.46
     desconoc
    -0.46
    хьтан
    -0.46
     kasarigan
    -0.45
    prä
    -0.44
     nombres
    -0.44
    ówn
    -0.44
    RTGC
    -0.43
    POSITIVE LOGITS
     myſelf
    0.88
     Monfieur
    0.84
     Efq
    0.80
     fevere
    0.74
     houſe
    0.71
     Cæsar
    0.71
     raiſ
    0.70
     poffible
    0.69
     ſche
    0.68
     depositphotos
    0.67
    Activations Density 0.068%

    No Known Activations