© 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. 1-CLT-HP
    7. 8868
    Prev
    Next
    INDEX
    Explanations

    joint injuries

    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
    WaitGroup
    -0.65
    IndentedString
    -0.56
    AndEndTag
    -0.56
    omo
    -0.55
     "")
    -0.54
     Familienname
    -0.52
    Diwedd
    -0.51
    StoryboardSegue
    -0.51
     INSEE
    -0.49
     ();
    -0.47
    POSITIVE LOGITS
     CGPoint
    0.52
     blade
    0.49
     globes
    0.48
    EDEFAULT
    0.48
    RectangleBorder
    0.47
    yntaxException
    0.47
    jface
    0.47
    viewWillAppear
    0.47
    enumii
    0.46
     pits
    0.46
    Activations Density 0.038%

    No Known Activations