© 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. 42330
    Prev
    Next
    INDEX
    Explanations

    hidden intentions

    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
     intent
    -1.66
     invisible
    -1.45
     intention
    -1.38
     Intent
    -1.38
     intents
    -1.35
     intentions
    -1.34
    intent
    -1.29
    invisible
    -1.23
     Invisible
    -1.20
     invis
    -1.13
    POSITIVE LOGITS
    localctx
    0.62
     begged
    0.50
    enterOuterAlt
    0.49
    ValueStyle
    0.48
    えられる
    0.48
    くださいませ
    0.47
     sure
    0.46
    copal
    0.46
    ikar
    0.46
     reclamar
    0.46
    Activations Density 1.519%

    No Known Activations