© 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. 5-CLT-HP
    7. 90941
    Prev
    Next
    INDEX
    Explanations

    such

    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
    ьаж
    -0.71
    TestingModule
    -0.59
     defaultstate
    -0.59
    DebuggerNonUser
    -0.59
     BoxFit
    -0.57
     invokingState
    -0.56
    +:+
    -0.53
    IUrlHelper
    -0.53
    enumi
    -0.52
    GroupLayout
    -0.52
    POSITIVE LOGITS
     myſelf
    0.82
     himſelf
    0.79
     themſelves
    0.75
     itſelf
    0.66
     chofe
    0.65
     Majefty
    0.65
     whoſe
    0.64
     becauſe
    0.63
     ſhe
    0.63
     uſed
    0.63
    Activations Density 0.000%

    No Known Activations