© 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. 4-CLT-HP
    7. 906
    Prev
    Next
    INDEX
    Explanations

    legal documents and dates

    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
     للاسماء
    -0.61
    Jîn
    -0.52
    )|^{
    -0.51
     *)__
    -0.49
    esez
    -0.47
     ويكيميديا
    -0.45
    canestro
    -0.44
     vari
    -0.44
    )_/¯
    -0.44
    OnAdd
    -0.43
    POSITIVE LOGITS
    featureID
    0.72
    tonsoft
    0.70
     cherchés
    0.61
    GEBURTSDATUM
    0.60
    ViewFeatures
    0.58
    Personendaten
    0.58
    談社
    0.57
     PeEnEo
    0.55
    /*
    0.55
     CHAPITRE
    0.55
    Activations Density 0.018%

    No Known Activations