© 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. 14158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    awakeFromNib
    -0.63
    Diwedd
    -0.62
    Geografía
    -0.59
     nakalista
    -0.56
    Билгалдахарш
    -0.56
     subject
    -0.54
    ombre
    -0.52
    corporated
    -0.52
    nextDouble
    -0.52
    twimg
    -0.52
    POSITIVE LOGITS
    //
    0.63
    DispatchToProps
    0.63
    transQ
    0.57
    modelBuilder
    0.55
    Personendaten
    0.55
    opis
    0.53
    #+#
    0.52
     makl
    0.50
    BeginContext
    0.49
     prostu
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.