© 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. 4-CLT-HP
    7. 1924
    Prev
    Next
    INDEX
    Explanations

    work

    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
     living
    -0.83
    live
    -0.83
    living
    -0.81
     live
    -0.79
    Live
    -0.74
     lived
    -0.72
    LIVE
    -0.70
     Live
    -0.69
    Living
    -0.68
     Living
    -0.68
    POSITIVE LOGITS
    addGap
    0.65
    Atsauces
    0.63
    wahati
    0.59
    spesies
    0.58
     rangs
    0.57
    AnchorStyles
    0.57
     isEqualToString
    0.55
    xpress
    0.54
    Brainz
    0.54
     الحره
    0.54
    Activations Density 0.004%

    No Known Activations