Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12702
    Prev
    Next
    INDEX
    Explanations

    sides

    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
     itſelf
    -0.68
    sider
    -0.53
     side
    -0.53
     faſt
    -0.52
     ſtand
    -0.52
     purpoſe
    -0.51
     houſe
    -0.50
    sided
    -0.50
    geri
    -0.50
     uſe
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.98
    AccessorTable
    0.77
    ArrowToggle
    0.68
     مشين
    0.68
     noDo
    0.68
    Datuak
    0.66
     oprot
    0.66
     estimés
    0.66
     <=",
    0.65
    setVerticalGroup
    0.65
    Activations Density 0.011%

    No Known Activations