© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94188
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     étoient
    -0.92
     étoit
    -0.90
     avoient
    -0.89
     automatiques
    -0.88
     sauvages
    -0.86
     normaux
    -0.86
     Houſe
    -0.84
     purpoſe
    -0.84
     nationaux
    -0.82
     Majefty
    -0.81
    POSITIVE LOGITS
    y
    0.66
     Ac
    0.65
     per
    0.63
     Mer
    0.62
     Par
    0.59
     Ak
    0.58
     y
    0.57
     par
    0.56
     gra
    0.56
     «
    0.56
    Activations Density 0.043%

    No Known Activations