© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    authenticity/truth

    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
    NewUrlParser
    -0.56
     ComVisible
    -0.54
    XmlIgnore
    -0.54
    ManagedBean
    -0.54
    OfClass
    -0.53
    IConfiguration
    -0.52
    =$((
    -0.51
    MAZ
    -0.50
    OfMonth
    -0.47
    cessed
    -0.47
    POSITIVE LOGITS
    CrossRef
    0.61
    Референце
    0.59
    URLException
    0.52
     réessayer
    0.52
    routeProvider
    0.52
    INSEE
    0.51
     bébés
    0.51
    ValueStyle
    0.51
     to
    0.51
    ⓧ
    0.50
    Activations Density 0.001%

    No Known Activations