© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41942
    Prev
    Next
    INDEX
    Explanations

    plo

    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
     real
    -0.60
    ereal
    -0.57
    ned
    -0.56
     plo
    -0.56
    eared
    -0.56
    EOUS
    -0.55
     Real
    -0.54
     con
    -0.54
     Sac
    -0.54
    éo
    -0.54
    POSITIVE LOGITS
    StructEnd
    0.60
    Xna
    0.60
    InputTagHelper
    0.58
    AsUp
    0.58
    RenderAtEndOf
    0.58
     onPage
    0.56
    MessageTagHelper
    0.56
     ATTENTION
    0.55
    vician
    0.55
    DockStyle
    0.54
    Activations Density 0.925%

    No Known Activations