© 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. 14828
    Prev
    Next
    INDEX
    Explanations

    Barney

    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
    s
    -0.63
    WriteAttribute
    -0.57
    цездатний
    -0.53
    sko
    -0.52
    sch
    -0.52
    ska
    -0.51
    sco
    -0.49
    sho
    -0.48
    WebElementEntity
    -0.47
     الرياضيه
    -0.47
    POSITIVE LOGITS
    trate
    0.57
    iah
    0.57
     themſelves
    0.56
    ector
    0.56
    eel
    0.55
    ſelves
    0.55
    IAH
    0.55
    脚注の使い方
    0.54
     betweenstory
    0.54
    ets
    0.52
    Activations Density 0.059%

    No Known Activations