© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4444
    Prev
    Next
    INDEX
    Explanations

    pain, discomfort

    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
    __':
    -0.66
    __":
    -0.65
    AIRES
    -0.63
     GetEnumerator
    -0.61
     onFailure
    -0.61
    
    -0.61
    riwal
    -0.59
     AttributeSet
    -0.59
    UpInside
    -0.58
     XCTest
    -0.58
    POSITIVE LOGITS
     répon
    0.57
     when
    0.47
     from
    0.47
    гава
    0.46
     after
    0.46
    理石
    0.44
     mercato
    0.44
     brune
    0.42
     while
    0.41
    ocene
    0.41
    Activations Density 0.001%

    No Known Activations