© 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. 1-CLT-HP
    7. 14022
    Prev
    Next
    INDEX
    Explanations

    poor

    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
     poor
    -0.69
    Poor
    -0.65
     Poor
    -0.63
    poor
    -0.58
     Che
    -0.52
     νε
    -0.51
    filepath
    -0.50
     pobre
    -0.49
     POOR
    -0.48
    ėj
    -0.48
    POSITIVE LOGITS
    mybatisplus
    0.69
    annica
    0.67
    oa̍t
    0.62
    TagHelper
    0.61
    AndEndTag
    0.58
    holders
    0.58
     '\\;'
    0.58
    TestingModule
    0.58
    Viitteet
    0.57
     &___
    0.55
    Activations Density 0.016%

    No Known Activations