© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42648
    Prev
    Next
    INDEX
    Explanations

    find

    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
     find
    -1.01
     Find
    -0.82
    find
    -0.82
     finds
    -0.78
    Find
    -0.70
     finding
    -0.67
    makeConstraints
    -0.66
     trouver
    -0.66
    finding
    -0.66
     finden
    -0.65
    POSITIVE LOGITS
     pleaſure
    1.10
     purpoſe
    1.08
     greateſt
    1.00
     ſta
    0.98
     Majefty
    0.97
     chofe
    0.94
     ſmall
    0.93
     ſtate
    0.91
     ſp
    0.90
     ſch
    0.89
    Activations Density 0.200%

    No Known Activations