© 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. 0-CLT-HP
    7. 94646
    Prev
    Next
    INDEX
    Explanations

    layering

    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
     layering
    -0.71
    hopper
    -0.69
    work
    -0.65
     behaviour
    -0.58
    ising
    -0.56
    works
    -0.55
    itize
    -0.53
    iness
    -0.51
    igen
    -0.47
     Hano
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.85
    ⓧ
    0.69
     @"/
    0.65
    kuuta
    0.64
    ).__
    0.63
     فريبيس
    0.61
     intptr
    0.60
    AddTagHelper
    0.60
     GenerationType
    0.59
     continúas
    0.58
    Activations Density 1.655%

    No Known Activations