© 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. 42920
    Prev
    Next
    INDEX
    Explanations

    showcase

    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
     showcase
    -0.79
     showcases
    -0.77
     portray
    -0.72
     portrays
    -0.72
     documenting
    -0.71
     referenties
    -0.68
     portrayed
    -0.67
     portraying
    -0.66
    Explicación
    -0.63
     Christmas
    -0.63
    POSITIVE LOGITS
     ujednoznacz
    0.65
     JpaRepository
    0.65
    PerformLayout
    0.64
    sizeCache
    0.62
     '{@
    0.61
     NavController
    0.55
    providedIn
    0.54
     BoxFit
    0.53
    ArgsConstructor
    0.52
    الحياه
    0.52
    Activations Density 0.465%

    No Known Activations