© 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. 1-CLT-HP
    7. 13761
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    الإنجليزية
    -0.47
    ’:
    -0.44
    ṃ
    -0.43
     riuscito
    -0.42
     wikipagina
    -0.42
    makeatletter
    -0.41
    ':
    -0.40
     Réponses
    -0.40
    nais
    -0.39
    béco
    -0.39
    POSITIVE LOGITS
    Попис
    0.78
    abestanden
    0.76
     kaynağından
    0.64
    ollectionView
    0.64
     kasarigan
    0.64
     surla
    0.63
    TSD
    0.59
    QMetaType
    0.58
    modelBuilder
    0.57
     виправивши
    0.57
    Activations Density 0.032%

    No Known Activations