© 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. 0-CLT-HP
    7. 38536
    Prev
    Next
    INDEX
    Explanations

    adult

    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
    Adult
    -0.90
     Adult
    -0.86
    ousness
    -0.79
    adult
    -0.74
    Adults
    -0.68
    adults
    -0.67
     Adults
    -0.66
    hood
    -0.60
     adulto
    -0.60
     Childhood
    -0.59
    POSITIVE LOGITS
    batore
    0.76
    FunctionFlags
    0.72
     дописавши
    0.61
     NSCoder
    0.60
     odkazy
    0.58
    styleType
    0.57
    featureID
    0.56
     informée
    0.54
    resave
    0.51
     houſe
    0.50
    Activations Density 0.367%

    No Known Activations