© 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. 97920
    Prev
    Next
    INDEX
    Explanations

    ships

    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
     season
    -0.56
     pastures
    -0.54
    StructEnd
    -0.54
     climate
    -0.54
     ſhe
    -0.53
     fubject
    -0.53
     ligiloj
    -0.52
     ſtate
    -0.52
    enfone
    -0.52
     purpoſe
    -0.51
    POSITIVE LOGITS
     preuves
    0.54
    giveness
    0.53
    fjspx
    0.51
     attendre
    0.51
    XmlAccessorType
    0.50
     decorativas
    0.47
     gratuitas
    0.47
     convaincre
    0.47
     magát
    0.46
    
    0.46
    Activations Density 0.002%

    No Known Activations