© 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. 43694
    Prev
    Next
    INDEX
    Explanations

    indeed

    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
     indeed
    -2.14
    indeed
    -1.62
     Indeed
    -1.53
    Indeed
    -1.45
     inderdaad
    -1.23
     effectivement
    -1.12
     efectivamente
    -1.09
     infatti
    -0.99
     fakty
    -0.86
     bowiem
    -0.79
    POSITIVE LOGITS
     cherchés
    0.59
    Népesség
    0.55
    ати
    0.52
     familiar
    0.51
    EndInit
    0.51
    DoubleQuotes
    0.51
    s
    0.51
    ship
    0.50
    die
    0.50
    ATES
    0.50
    Activations Density 0.161%

    No Known Activations