© 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. 1-CLT-HP
    7. 9880
    Prev
    Next
    INDEX
    Explanations

    eel

    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
    
    -0.61
    первых
    -0.55
    Hentet
    -0.54
    IMPORTED
    -0.52
    ValueStyle
    -0.50
    \{\\
    -0.48
    Provided
    -0.47
     ſtand
    -0.47
    räck
    -0.46
     faveur
    -0.45
    POSITIVE LOGITS
     mergeFrom
    0.77
    featureID
    0.65
    álním
    0.57
    Datuak
    0.56
    CodeAttribute
    0.56
    ing
    0.55
     ControllerBase
    0.55
    exitRule
    0.54
     ddelweddau
    0.54
    chain
    0.53
    Activations Density 0.003%

    No Known Activations