© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95611
    Prev
    Next
    INDEX
    Explanations

    hur

    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
    Negative Logits
    hur
    -0.73
     AssemblyTitle
    -0.63
    har
    -0.54
     unknownFields
    -0.54
    #+#
    -0.54
    pepe
    -0.53
    hara
    -0.52
    hra
    -0.51
     TestBed
    -0.50
     Pandey
    -0.47
    POSITIVE LOGITS
     חיצוניים
    0.68
    TagMode
    0.67
    yntaxException
    0.67
     متعلقه
    0.66
     Houſe
    0.65
    bonucle
    0.63
     Theſe
    0.63
     themſelves
    0.59
     ſmall
    0.58
    Captor
    0.57
    Activations Density 0.298%

    No Known Activations