© 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. 5-CLT-HP
    7. 5615
    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
    Personendaten
    -0.53
    VIAF
    -0.49
    sibilité
    -0.45
     يتيمه
    -0.45
    BuildContext
    -0.44
     травня
    -0.43
    úmer
    -0.43
     Im
    -0.43
    hical
    -0.41
     solucion
    -0.41
    POSITIVE LOGITS
    .~(\
    0.64
    Obrázky
    0.60
    Erreferentziak
    0.59
    ordinaire
    0.59
     незавершена
    0.58
    htub
    0.58
    GBT
    0.57
    ftagPool
    0.56
    脚注の使い方
    0.55
    ilirsiniz
    0.54
    Activations Density 0.008%

    No Known Activations