© 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. 9594
    Prev
    Next
    INDEX
    Explanations

    single

    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
     single
    -1.30
    single
    -1.23
     Single
    -1.16
    Single
    -1.13
     SINGLE
    -1.05
    SINGLE
    -0.84
     singolo
    -0.82
    单
    -0.76
    シングル
    -0.73
     singoli
    -0.72
    POSITIVE LOGITS
    apimachinery
    0.75
    AsUp
    0.74
    ChildScrollView
    0.69
     <=",
    0.68
    ंदीखरीदारी
    0.66
    BoxShadow
    0.66
    basicConfig
    0.63
     AspNetCore
    0.63
     settlements
    0.60
     sureties
    0.59
    Activations Density 0.032%

    No Known Activations