© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96251
    Prev
    Next
    INDEX
    Explanations

    election years

    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
    енча
    -0.94
     wireType
    -0.92
    期刊论文
    -0.86
     initComponents
    -0.84
     الحره
    -0.83
    tagHelperRunner
    -0.82
    Tikang
    -0.81
     propOrder
    -0.79
    AccessorTable
    -0.79
    EDEFAULT
    -0.78
    POSITIVE LOGITS
    createTextNode
    0.36
    чется
    0.36
    ละ
    0.35
    γρά
    0.35
     act
    0.34
    TypeString
    0.34
     TV
    0.33
    Clickable
    0.32
     physical
    0.32
     **
    0.32
    Activations Density 0.008%

    No Known Activations