© 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. 95280
    Prev
    Next
    INDEX
    Explanations

    negative downturns

    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
     worse
    -1.34
     Worse
    -1.33
    Worse
    -1.23
    worse
    -1.14
     esternos
    -0.84
     exaggerated
    -0.81
     leſs
    -0.81
     pior
    -0.80
     ſeveral
    -0.78
    SharedDtor
    -0.78
    POSITIVE LOGITS
    RectangleBorder
    0.50
    rzost
    0.47
    mering
    0.47
     arran
    0.46
    atis
    0.46
     remp
    0.45
    ive
    0.45
    enite
    0.44
     Bro
    0.42
     Dog
    0.41
    Activations Density 0.025%

    No Known Activations