© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97115
    Prev
    Next
    INDEX
    Explanations

    enjoyment

    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
     wonderful
    -0.58
     lovely
    -0.56
     fabulous
    -0.49
     terrific
    -0.47
     beautiful
    -0.47
     estup
    -0.46
     delightful
    -0.45
    CLUDE
    -0.45
     delicious
    -0.44
    IRMED
    -0.44
    POSITIVE LOGITS
     autorytatywna
    1.03
     OFDb
    0.94
    Personendaten
    0.92
    principalTable
    0.85
    Autoritní
    0.83
    ValueStyle
    0.79
    GEBURTSDATUM
    0.79
     disambiguazione
    0.78
     propOrder
    0.75
    contentLoaded
    0.72
    Activations Density 0.000%

    No Known Activations