© 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. 43308
    Prev
    Next
    INDEX
    Explanations

    council and sec

    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
    lee
    -0.67
     curling
    -0.62
    pai
    -0.59
     curled
    -0.57
    ArrowToggle
    -0.57
     synthesis
    -0.56
    hae
    -0.52
     Synthesis
    -0.52
    auti
    -0.52
    mybatisplus
    -0.50
    POSITIVE LOGITS
    stateProvider
    0.75
    ftagPool
    0.73
     виправивши
    0.65
    Datuak
    0.60
    theless
    0.59
    StreetMap
    0.57
     مشين
    0.55
     hObject
    0.55
    AccessorTable
    0.54
    WebVitals
    0.54
    Activations Density 0.103%

    No Known Activations