© 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. 20-CLT-HP
    7. 73545
    Prev
    Next
    INDEX
    Explanations

    disintegration

    np_max-act-logits · 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
    RegressionTest
    -0.60
    Hentet
    -0.58
     Ooster
    -0.56
     betweenstory
    -0.55
     Filling
    -0.55
     Fill
    -0.53
     يتيمه
    -0.52
     filling
    -0.50
    #
    -0.49
    
    -0.49
    POSITIVE LOGITS
     dissolve
    0.68
     unc
    0.66
     thin
    0.65
     break
    0.65
     loosen
    0.64
     clear
    0.60
     dis
    0.59
     liqu
    0.59
     Dissolve
    0.59
     melt
    0.57
    Activations Density 0.000%

    No Known Activations