© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43623
    Prev
    Next
    INDEX
    Explanations

    )

    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
    homonymie
    -0.71
    ,
    -0.65
    .
    -0.54
    UnitTesting
    -0.51
    RegistryLite
    -0.50
     оригіналу
    -0.50
    ers
    -0.49
    addCriterion
    -0.49
    ngths
    -0.48
    ConstraintMaker
    -0.48
    POSITIVE LOGITS
     ſmall
    1.06
     purpoſe
    1.05
     myſelf
    1.05
     reaſon
    1.01
     pleaſure
    0.99
     Efq
    0.98
     perſon
    0.98
     Monfieur
    0.98
     Majefty
    0.94
     ſtate
    0.92
    Activations Density 0.239%

    No Known Activations