© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93692
    Prev
    Next
    INDEX
    Explanations

    Names/References to People

    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
    ella
    -0.81
     Bur
    -0.78
     las
    -0.68
     Je
    -0.64
     Bor
    -0.64
     to
    -0.63
     red
    -0.62
    ico
    -0.62
     los
    -0.61
     non
    -0.59
    POSITIVE LOGITS
     Majefty
    0.97
     themſelves
    0.90
     purpoſe
    0.90
     feroit
    0.88
     myſelf
    0.88
     greateſt
    0.86
     pleaſure
    0.86
     ſtate
    0.85
     Anſ
    0.84
     ſeveral
    0.83
    Activations Density 0.120%

    No Known Activations