© 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. 1-CLT-HP
    7. 10124
    Prev
    Next
    INDEX
    Explanations

    lie

    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
     utafitiHapana
    -0.50
     lie
    -0.47
     BufferedImage
    -0.47
    Parcelize
    -0.45
     lies
    -0.45
     civile
    -0.41
    Reentrant
    -0.40
    tský
    -0.40
     Sit
    -0.39
     stems
    -0.39
    POSITIVE LOGITS
    ArgsConstructor
    0.71
    findpost
    0.69
    存于互联网档案馆
    0.68
    rolid
    0.66
     nakalista
    0.65
    ActionTypes
    0.63
    IndentedString
    0.63
    ngdoc
    0.62
     enjoined
    0.61
    ]<<"
    0.58
    Activations Density 0.004%

    No Known Activations