© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96671
    Prev
    Next
    INDEX
    Explanations

    are

    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
     Vielleicht
    -1.06
     perhaps
    -1.05
     vielleicht
    -1.05
     maybe
    -1.04
    Maybe
    -1.01
    perhaps
    -1.01
     misschien
    -0.95
    Perhaps
    -0.95
     Maybe
    -0.93
    maybe
    -0.93
    POSITIVE LOGITS
     basically
    0.54
     noqa
    0.53
    OCCURRED
    0.50
    基本的に
    0.49
    basically
    0.49
    /*
    0.48
     totiž
    0.47
    essentially
    0.47
    msgTypes
    0.46
     básicamente
    0.45
    Activations Density 0.036%

    No Known Activations