© 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. 209
    Prev
    Next
    INDEX
    Explanations

    Many

    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
     PROCEEDINGS
    -0.57
     Савезне
    -0.55
     Comprometido
    -0.54
    cedures
    -0.54
    Spoljašnje
    -0.54
    Portail
    -0.53
    सन्दर्भ
    -0.53
    LEn
    -0.52
    InjectAttribute
    -0.51
     ("
    -0.50
    POSITIVE LOGITS
     Check
    0.51
     check
    0.49
     Seeing
    0.48
     visit
    0.48
     try
    0.48
    parsedMessage
    0.47
     use
    0.46
    发表于
    0.45
     ask
    0.45
     do
    0.45
    Activations Density 0.000%

    No Known Activations