© 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. 5-CLT-HP
    7. 93807
    Prev
    Next
    INDEX
    Explanations

    current

    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
    tagHelperRunner
    -0.87
    ErrUnexpectedEOF
    -0.65
    AddTagHelper
    -0.63
    SharedDtor
    -0.63
     kasarigan
    -0.61
    ItemBackground
    -0.60
    graphicx
    -0.60
     AttributeSet
    -0.60
     gynhyrchwyd
    -0.60
     становника
    -0.59
    POSITIVE LOGITS
     trends
    0.57
     status
    0.54
    tagHelper
    0.48
     issues
    0.44
     developments
    0.43
     getStatus
    0.43
     challenges
    0.43
     directions
    0.42
     debates
    0.41
     وض
    0.41
    Activations Density 0.001%

    No Known Activations