© 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. 20-CLT-HP
    7. 77830
    Prev
    Next
    INDEX
    Explanations

    chemical agents/processes

    np_max-act-logits · 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
    ftagPool
    -0.84
     defaultstate
    -0.78
     agents
    -0.78
     themſelves
    -0.76
    клопе
    -0.76
    ArrowToggle
    -0.75
     Halen
    -0.75
     Agents
    -0.74
    hops
    -0.74
    AccessorTable
    -0.73
    POSITIVE LOGITS
     makeStyles
    0.36
     FormBuilder
    0.35
     ag
    0.34
     vân
    0.32
    gic
    0.32
    wapV
    0.30
     sub
    0.30
     а
    0.29
    itemBuilder
    0.29
    ag
    0.28
    Activations Density 0.001%

    No Known Activations