© 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. 94063
    Prev
    Next
    INDEX
    Explanations

    flex

    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
     flex
    -0.91
    flex
    -0.88
    WriteBarrier
    -0.78
    Flex
    -0.73
     Flex
    -0.71
     onBind
    -0.70
     >=",
    -0.66
    TagMode
    -0.65
    AutoScaleMode
    -0.62
     Mag
    -0.58
    POSITIVE LOGITS
    retudo
    0.55
     vägen
    0.49
     purpoſe
    0.48
     épaules
    0.45
     sogget
    0.44
     feroit
    0.44
     étoit
    0.44
     reaſon
    0.43
    numerusform
    0.43
     forskj
    0.43
    Activations Density 0.248%

    No Known Activations