© 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. 94112
    Prev
    Next
    INDEX
    Explanations

    profit

    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
    s
    -0.52
     da
    -0.50
    mans
    -0.48
    MANS
    -0.46
     ca
    -0.46
     dai
    -0.45
     lente
    -0.44
    profit
    -0.43
     bot
    -0.43
     rot
    -0.42
    POSITIVE LOGITS
     pleaſure
    1.41
     purpoſe
    1.35
     houſe
    1.30
     myſelf
    1.28
     ſeveral
    1.26
     ſtate
    1.25
     itſelf
    1.23
     raiſ
    1.21
     greateſt
    1.21
     ſmall
    1.20
    Activations Density 0.263%

    No Known Activations