© 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. 0-CLT-HP
    7. 93604
    Prev
    Next
    INDEX
    Explanations

    permeability

    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
     permeability
    -1.98
     Permeability
    -1.59
    meability
    -0.98
    MENAFN
    -0.73
     continúas
    -0.69
    extAlignment
    -0.67
    
    -0.66
     permeable
    -0.65
     Wainwright
    -0.63
     médic
    -0.60
    POSITIVE LOGITS
    InitVars
    0.67
     propOrder
    0.65
    epam
    0.57
    hljs
    0.54
    HandlerContext
    0.52
    cheur
    0.47
    CORBA
    0.45
    BrowserModule
    0.45
    verwijspagina
    0.45
    keras
    0.44
    Activations Density 1.295%

    No Known Activations