© 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. 94533
    Prev
    Next
    INDEX
    Explanations

    mixed content, various contexts

    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
     suite
    -0.47
    fbox
    -0.47
    去了
    -0.47
    حف
    -0.47
     order
    -0.46
     box
    -0.45
     vár
    -0.44
     énergétique
    -0.44
    ApiException
    -0.44
    主的
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.02
     propOrder
    1.01
    Personendaten
    0.91
    WithIOException
    0.88
     Roskov
    0.87
     nahilalakip
    0.87
    Lähteet
    0.86
     MainAxisSize
    0.86
    ImageContext
    0.85
    Przypisy
    0.84
    Activations Density 2.320%

    No Known Activations