© 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. 96508
    Prev
    Next
    INDEX
    Explanations

    regions

    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
     يتيمه
    -0.61
    IntoConstraints
    -0.52
    енча
    -0.48
     Réponses
    -0.46
    DeleteBehavior
    -0.45
    FormTagHelper
    -0.42
    rated
    -0.42
    acki
    -0.41
     Amish
    -0.40
    ंदीखरीदारी
    -0.40
    POSITIVE LOGITS
     oreilles
    0.67
     rayures
    0.66
     remonter
    0.65
     coû
    0.65
     ainfi
    0.64
    horabuena
    0.64
     quelcon
    0.63
     verksamhet
    0.63
     inconvénients
    0.63
     mauvaises
    0.62
    Activations Density 0.001%

    No Known Activations