© 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. 5-CLT-HP
    7. 93446
    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
     tarko
    -0.66
    httphttps
    -0.60
    neté
    -0.56
     confé
    -0.54
    éb
    -0.53
     legati
    -0.52
     riuscito
    -0.51
     ovunque
    -0.50
    Obrázky
    -0.49
     Außer
    -0.48
    POSITIVE LOGITS
    argout
    0.87
    HtmlAttribute
    0.77
     TextAppearance
    0.65
    EndInit
    0.61
    ddots
    0.56
    ="?
    0.56
     PeEnEo
    0.55
    UserScript
    0.54
    andidate
    0.53
    createCanvas
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.