© 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. 1-CLT-HP
    7. 11468
    Prev
    Next
    INDEX
    Explanations

    jecture, interstitial

    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
    jecture
    -0.74
    دانشنامهٔ
    -0.68
    dimer
    -0.68
     dimer
    -0.67
    EndInit
    -0.66
     TextAppearance
    -0.66
     disambiguazione
    -0.66
     typelib
    -0.63
     HasFactory
    -0.60
     conjecture
    -0.60
    POSITIVE LOGITS
    AddTagHelper
    0.68
    المناصب
    0.45
     /\.
    0.45
     المعيارى
    0.44
    ourge
    0.44
    Revenir
    0.43
    SharedCtor
    0.43
    veret
    0.43
    Hahahahaha
    0.43
     rire
    0.42
    Activations Density 0.207%

    No Known Activations