© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     تضيفلها
    -0.67
     <>",
    -0.56
     females
    -0.53
    exitRule
    -0.52
     Maladies
    -0.51
    girls
    -0.51
     girls
    -0.50
     findAll
    -0.50
    ollectionView
    -0.49
     lesbians
    -0.48
    POSITIVE LOGITS
    esModule
    0.72
     الحره
    0.64
    PrototypeOf
    0.56
     Majefty
    0.54
     greateſt
    0.52
     Melhor
    0.52
    Real
    0.50
     Real
    0.50
    real
    0.50
     beſt
    0.50
    Activations Density 0.033%

    No Known Activations