© 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. 4-CLT-HP
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    zos

    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
    Geplaatst
    -0.89
     lenker
    -0.61
    Chham
    -0.53
    Personendaten
    -0.52
     Wikimedijinoj
    -0.52
    featureID
    -0.52
    MessageOf
    -0.52
    oredCriteria
    -0.51
     bulunabilir
    -0.51
    WebVitals
    -0.50
    POSITIVE LOGITS
    ваги
    0.51
    UnitTesting
    0.51
    Memorial
    0.50
     recevrez
    0.49
    YNAMICS
    0.48
    ={({
    0.47
    dienste
    0.46
     Yamamoto
    0.46
     MEMORIAL
    0.45
    miljø
    0.45
    Activations Density 0.002%

    No Known Activations