© 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. 9159
    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
     Schaefer
    -0.75
     &___
    -0.63
    orsese
    -0.62
    stücke
    -0.59
    RegistryLite
    -0.59
    شهاد
    -0.56
    الحياه
    -0.56
     snippetHide
    -0.55
    defineProperty
    -0.54
     الحره
    -0.53
    POSITIVE LOGITS
     OnInit
    0.60
     Bung
    0.53
    ton
    0.52
    hut
    0.52
    master
    0.48
    struck
    0.48
    bria
    0.48
    abank
    0.47
    butt
    0.47
    le
    0.47
    Activations Density 0.428%

    No Known Activations